tag:blogger.com,1999:blog-76308106066542500772012-02-17T13:06:27.059-08:00klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.comBlogger1811100tag:blogger.com,1999:blog-7630810606654250077.post-64987850134734455252012-02-10T14:37:00.001-08:002012-02-10T14:39:41.088-08:00<p>THIS IS ONLY AN EXAMPLE AND IS NOT INVESTMENT ADVICE. ACTING ON THIS WILL LOSE LOTS OF MONEY.</p> <p><a href="http://systematicinvestor.wordpress.com/" target="_blank">Systematic Investor Blog</a> (be sure to check out the site) offers extremely good examples of how to use R in finance.&nbsp; Since I firmly believe more examples are always better, I wanted to provide an additional very simple example of how to use his <a href="https://github.com/systematicinvestor/SIT">Systematic Investor Toolbox (SIT)</a> for systems development.&nbsp; This will provide a building block for a series of posts similar to my <a href="http://timelyportfolio.blogspot.com/2011/07/quantstrat-to-build-on-part-6.html">A Quantstrat to Build On Part 6</a>.&nbsp; We’ll use our good old count up/down (CUD) indicator on the S&amp;P 500 Index and compare it to <a href="http://www.mebanefaber.com" target="_blank">Mebane Faber’s</a> 10 month moving average.</p> <p>I know this is not pretty, but I wanted to start with as simple a base as possible.&nbsp; Any loyal readers will already have known that CUD is not so great at making money.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/hw9waozO6_s2w18-0gd6CdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-8qPGVTPmrKo/TzWbVoo-XbI/AAAAAAACH1s/HAXQZWPI7t8/s640/Rplot05.png" width="320" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/115099029813395778077/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table><a href="https://gist.github.com/1793607" target="_blank">R code in GIST</a>: <script src="https://gist.github.com/1793607.js?file=use%20of%20systematic%20investor%20part%201.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-6498785013473445525?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-66622154372988664272012-02-06T13:35:00.001-08:002012-02-06T13:35:35.621-08:00<p>With all my recent focus on reporting and visualization, you might think that I have the investments all figured out.&nbsp; Unfortunately, that is not the case, and I will resume more standard investment and systems posts soon.&nbsp; I did want to share what I think are two more beautiful Growth of a $1 visualizations.&nbsp; Although my lattice code is far from tight, I think the result is fairly good using and modifying some of the Economist style graphs offered in latticeExtra.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/kDTZYNcgnUoXZ7xt801EgdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-EgCz3RQZcHI/TzBGzyMenJI/AAAAAAACH1Q/M2Q1ZcOQt_M/s800/lattice%2520cumul%2520growth.png" width="640" height="450"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>With a little modification, the chart.CumReturns from PerformanceAnalytics can also look very similar.&nbsp; I will let you choose your favorite.&nbsp; However, the lattice version will much more likely appear in my reports.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/ixWx_FgJUAxBWxVOmBH35dMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-pR3iMRTW36w/TzBGz1__Y1I/AAAAAAACH1U/QbwtVbOAhvo/s800/PerformanceAnalytics%2520cumul%2520growth.png" width="640" height="450"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1754891" target="_blank">Get code from GIST:</a></p><script src="https://gist.github.com/1754891.js?file=cumul%20growth%20of%20dollar.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-6662215437298866427?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-52177386848646258082012-02-01T14:18:00.001-08:002012-02-01T14:22:32.821-08:00<p>I am extremely excited to share the announcement that Jim Rogers will present at the <a href="http://www.cfasociety.org/alabama/Pages/default.aspx" target="_blank">CFA Society of Alabama Annual Dinner February 29</a> at Barber Motorsports Museum in Birmingham.&nbsp; I believe there is still room for anyone who might like to attend.&nbsp; <a href="http://online.barrons.com/public/search/results.html?KEYWORDS=&quot;JACK WILLOUGHBY&quot;&amp;ARTICLESEARCHQUERY_PARSER=bylineOR" target="_blank">Barron’s senior editor Jack Willoughby</a> will moderate.&nbsp; Congratulations to the CFA Society of Alabama on a high-powered event.</p> <p><a href="http://www.cfasociety.org/alabama" target="_blank"><img style="background-image: none; border-bottom: 0px; border-left: 0px; padding-left: 0px; padding-right: 0px; display: inline; border-top: 0px; border-right: 0px; padding-top: 0px" title="image" border="0" alt="image" src="http://lh5.ggpht.com/-u2nEbMLz_ug/Tym6SF2TDpI/AAAAAAACH0s/c2yB2vBNmOo/image%25255B19%25255D.png?imgmax=800" width="368" height="509"></a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-5217738684864625808?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-41179097492685537812012-01-26T15:00:00.001-08:002012-01-26T15:00:12.127-08:00<p>I believe my survey experiment <a href="http://timelyportfolio.blogspot.com/2012/01/survey-time.html">Survey Time</a> illustrated later in this post and in <a href="http://timelyportfolio.blogspot.com/2012/01/googles-visualization-of-survey.html">Google’s Visualization of Survey Responses</a> mainly pointed out how ignorant I am about the very complicated science of surveying from building the survey to the visualization of the results.&nbsp; Thanks very much though to all the fine folks who responded, and I’m always open to suggestions through this survey or the traditional methods of commenting, Twittering, or emailing.&nbsp; I also really appreciate Markus Gesmann’s post <a href="http://lamages.blogspot.com/2012/01/feedback-from-vignette-survey.html">Feedback from vignette survey</a> for giving me the idea and Michael Friendly’s <a title="http://datavis.ca/papers/casm/casm.pdf" href="http://datavis.ca/papers/casm/casm.pdf">http://datavis.ca/papers/casm/casm.pdf</a> for helping me think through the visualization.&nbsp; I have not had a chance to read, but</p><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=1580256600&amp;nou=1&amp;ref=qf_sp_asin_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe> <p>this appears to be the Bible of survey and non-quantitative visualization.&nbsp; Also, I got a big kick out of this <a href="http://books.google.com/books?id=zvF5wb12E0wC&amp;printsec=frontcover&amp;dq=michael+friendly&amp;hl=en&amp;sa=X&amp;ei=_dMhT9KlG6KS0QHYl93SCA&amp;ved=0CDsQ6AEwAQ">Advanced logo: a language for learning</a> since at 7 seven years old the Logo turtle introduced me to programming and assured my destiny of a lifetime of geekdom.</p> <p>Unfortunately, this visualization is not my most stunning or best work, but I wanted to make sure that I shared for anyone that might find it helpful or inspirational.&nbsp;&nbsp; There are lots of ways to get Google Docs into R, but I choose the easiest and least elegant.&nbsp; Google allows publishing to the web as csv.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/lXXohg4640DyeIPUwrTuLNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-51O7yOAZDk8/TyHWdrccipI/AAAAAAACHg4/RP4JDzc5TFs/s800/google%2520publish%2520step%25201.png" width="469" height="566"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/vfC2zTtR3Jx0ajI0mZ1eyNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-kCOVg6oZSiw/TyHWgwB7RZI/AAAAAAACHhA/vSnl-MIlX-s/s800/google%2520publish%2520step%25202.png" width="615" height="641"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Then we can simply use the base read.csv file to access the results to get the following visualization of the survey.&nbsp; If you want to see the full set of results, go to <a title="https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E" href="https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E">https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E</a>.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/lW3mgghLp0C4P2IqvGtlHdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-mVLZiSzK-So/TyHWg081X-I/AAAAAAACHhE/cV__-tdxuXE/s640/survey%2520results.jpeg" width="480" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1685654" target="_blank">R code in Gist (click to download)</a>&nbsp; One comment recommended that I do not show the code in the post.&nbsp; Please let me know if you agree or disagree.</p> <p>Thanks again to everyone who responded and all my loyal readers.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4117909749268553781?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-70461470196458960662012-01-18T14:25:00.001-08:002012-01-18T19:07:37.734-08:00<p>Inspired by the post <a href="http://googleadsdeveloper.blogspot.com/2012/01/more-office-hours-in-2012.html">More Office Hours in 2012</a> and the <a href="http://timelyportfolio.blogspot.com/2012/01/googles-visualization-of-survey.html" target="_blank">survey results</a>, I thought I would offer office hours while blogging/playing in R.&nbsp; If anyone is interested, please send me an email at kent.russell at timelyportfolio.com, or just look for me at <a href="https://talkgadget.google.com/hangouts/extras/talk.google.com/timelyportfolio%2520playing%2520in%2520r?authuser=0&amp;hl=en&amp;eid=" target="_blank">Google Hangout</a>.&nbsp; I’ll do my first 1/18/2012 from 4:27 pm to 5:00 pm central.</p> <p>&nbsp;</p> <p><em><font color="#646b86">follow up: got 3 participants in my Hangout experiment all through <a href="http://hangoutcanopy.com">http://hangoutcanopy.com</a>, but unfortunately nobody knew about R or my blog.&nbsp; Maybe I should switch to an unlisted Hangout if that is possible.</font></em></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-7046147019645896066?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-45568047462807271022012-01-17T14:27:00.001-08:002012-01-17T14:27:05.118-08:00<p>As I try to develop the most beautiful and informative visualization of the survey responses <a href="http://timelyportfolio.blogspot.com/2012/01/survey-time.html">Survey Time</a>, I thought I should have a base case on which I could improve.&nbsp; Fortunately, Google offers a visualization, which I think is actually pretty good.&nbsp; Thanks to everyone who has responded.&nbsp; Please respond (takes less than 1 minute) if you have not yet.</p> <div style="width: 668px" id="__ss_11118678"><strong style="margin: 12px 0px 4px; display: block"><a title="Survey Results (google vis)" href="http://www.slideshare.net/timelyportfolio/survey-results-google-vis" target="_blank">Survey Results (google vis)</a></strong> <iframe height="714" marginheight="0" src="http://www.slideshare.net/slideshow/embed_code/11118678" frameborder="0" width="668" marginwidth="0" scrolling="no"></iframe> <div style="padding-bottom: 12px; padding-left: 0px; padding-right: 0px; padding-top: 5px">View more <a href="http://www.slideshare.net/" target="_blank">documents</a> from <a href="http://www.slideshare.net/timelyportfolio" target="_blank">timelyportfolio</a> </div></div> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4556804746280727102?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-4674578386665744072012-01-17T09:56:00.001-08:002012-01-17T09:56:21.797-08:00<p>Since I explored the relationship between the <a href="http://timelyportfolio.blogspot.com/2012/01/are-we-japanese.html" target="_blank">Japanese Yen and the US 10y Treasury Yield on Friday</a>, I thought it might be worthwhile to extend the exploration to a much broader range of currencies. I personally am most interested on how Asian Central Bank manipulation has affected the US 10y yield, and how if that changes what might be the impact to world markets. Please let me know your thoughts.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/vNyR3RcACTLk0NEjW6d1NNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-IHuzX3BAE88/TxW1sNscs5I/AAAAAAACHRI/xDuh32L0bds/s640/currencies%252520and%252520us10y.jpeg" width="640" height="586"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/sKG11PT6y3ua9ZLojnxEL9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-ZrOtR2bUN9Y/TxW1sGO0AMI/AAAAAAACHRE/O4mrhlozJBk/s640/currencies%252520and%252520us10y%252520pca.jpeg" width="640" height="606"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1627742" target="_blank">R code in GIST:</a></p><script src="https://gist.github.com/1627742.js?file=currencies%20and%20US10y.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-467457838666574407?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-68152717298744052632012-01-13T15:13:00.001-08:002012-01-16T08:02:52.880-08:00<p>Most of the discussion trying to determine if the U.S. is Japan 20 years later focuses on the economy and the stock market.&nbsp; However, one of the biggest and most persistent correlations between Japan and the U.S. are the Japanese Yen and the U.S. 10 Year Treasury Yield.&nbsp; I think it is essential to really try to explore this relationship to help determine “How Japanese are we?”&nbsp; With the US $ in decline, it is hard to imagine the continued persistence of this dynamic. <em>(Thanks reader teramonagi for catching an error.)</em></p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Q06dPUtDbPqhJ4BaRzk46NMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-1iA3l8SkmEk/TxRJymu68eI/AAAAAAACGW0/CQvxzGSQ1tw/s800/yen%252520and%252520us10y.jpeg" width="668" height="610"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>For additional thoughts on Japan, please see my post <a href="http://timelyportfolio.blogspot.com/2011/02/japan-intentional-or-accidental-pursuit.html">Japan Intentional or Accidental Pursuit of Deflation</a>.</p> <p><a href="https://gist.github.com/1609266" target="_blank">R code in GIST:</a></p><script src="https://gist.github.com/1609266.js?file=yen%20and%20us10y.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-6815271729874405263?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com5tag:blogger.com,1999:blog-7630810606654250077.post-90648323870893463112012-01-12T13:23:00.001-08:002012-01-12T13:23:24.844-08:00<p>In <a href="http://timelyportfolio.blogspot.com/2012/01/extreme-bond-returns.html">Extreme Bond Returns</a>, I did not consider the context of extreme bond returns, so let’s examine annual returns for the Dow Jones Industrial Average when bonds experience extreme annual returns.&nbsp; I was very surprised that stocks performed extremely well when bonds also did extremely well.&nbsp; Unfortunately, 6 of the 8 periods all occurred during the incredible 30 year bond bull 1980-2011, so it is difficult to come to any universal conclusions.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/k-Bfj28JSpBxprbqP6JcwdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-9arpb6h7NCY/Tw8yeFnj_dI/AAAAAAACGWE/YAD1fJMPrAA/s640/annual%252520return%252520djia%252520and%252520aaa.jpeg" width="640" height="432"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>And a little different look with lattice</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/tDRuEFMFvjgy0hx9FeKqEtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-cotkzKML9JU/Tw9Oh8qTJFI/AAAAAAACGWU/lbpEN7wFHIY/s640/dotplot%252520of%252520annual%252520returns.jpeg" width="585" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1603209" target="_blank">R code from GIST:</a></p><script src="https://gist.github.com/1603209.js?file=stocks%20with%20extreme%20bonds.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-9064832387089346311?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-46778000180162219292012-01-12T08:36:00.001-08:002012-01-12T08:51:15.698-08:00<p>In <a href="http://timelyportfolio.blogspot.com/2011/08/real-squeeze.html">Real Squeeze</a>, <a href="http://timelyportfolio.blogspot.com/2011/08/1-guaranteed-real-real-return-yummy.html">-1% Guaranteed Real Real Return! Yummy??</a>, and <a href="http://timelyportfolio.blogspot.com/2011/04/historical-sources-of-bond-returns.html">Historical Sources of Bond Returns</a>, I offer some historical perspective on the only sources of bond returns: inflation, real returns, and credit.&nbsp; Assuming no credit risk in US Treasuries (probably not a good assumption given this <a href="http://www.bloomberg.com/quote/CT786916:IND" target="_blank">Bloomberg quote on CDS on US Treasuries</a>), the formula is fixed, and all inputs except inflation are provided ex-ante.&nbsp; While bond prices can fluctuate wildly (<a href="http://timelyportfolio.blogspot.com/2012/01/extreme-bond-returns.html">Extreme Bond Returns</a>), the experience over the life of a bond and a bond index is predetermined by the yield to maturity.&nbsp; Unfortunately, that guaranteed experience in inflation or deflation is not so pleasant.</p> <p>While everyone should know R, I understand that some readers would prefer an easier route.&nbsp; <a href="http://research.stlouisfed.org/fred2" target="_blank">FRED</a> as usual comes to the rescue.&nbsp; Unfortunately though, labeling is not allowed.&nbsp; The codes can be translated as follows:</p> <ul> <li>DBAA = total return on BAA <li>DBAA – (DGS10 – DFII10) = credit return <li>DGS10 – DFII10 = inflation (expected) <li>DGS10 = real return</li></ul> <p><img src="http://research.stlouisfed.org/fredgraph.png?g=4k1"></p> <p>In the spirit of continuous improvement, here is the chart now using lattice and latticeExtra.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/uG1OwUW6q6Hop8VPS683MtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-t9TyTzDbCTI/Tw8PCGMP0bI/AAAAAAACGV0/e03vLmkBoyQ/s640/lattice%252520plot%252520of%252520sources.jpeg" width="640" height="578"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1601483" target="_blank">R code now in GIST:</a></p><script src="https://gist.github.com/1601483.js?file=bondreturnsources.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4677800018016221929?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-43944766077172539252012-01-11T13:55:00.001-08:002012-01-17T14:28:23.142-08:00<p>After I completed the vignette survey <a title="http://lamages.blogspot.com/2012/01/feedback-from-vignette-survey.html" href="http://lamages.blogspot.com/2012/01/feedback-from-vignette-survey.html">http://lamages.blogspot.com/2012/01/feedback-from-vignette-survey.html</a>, I was amazed with the process, functionality, and potential R integration from Google Docs forms.&nbsp; I just had to make one of my own. As I try to say in each post, I love comments, suggestions, and feedback.&nbsp; Please let me know what you think.</p> <p>Anyone who would like to see the results real-time, please see <a title="https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E" href="https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E">https://docs.google.com/spreadsheet/ccc?key=0AieeEIaS0AOsdGpvbTltd0pLZGh1cjRjZnlaV3pVY1E</a> and Google’s visualization <a title="http://www.slideshare.net/timelyportfolio/survey-results-google-vis" href="http://www.slideshare.net/timelyportfolio/survey-results-google-vis" target="_blank">http://www.slideshare.net/timelyportfolio/survey-results-google-vis</a>.</p><iframe height="985" marginheight="0" src="https://docs.google.com/spreadsheet/embeddedform?formkey=dGpvbTltd0pLZGh1cjRjZnlaV3pVY1E6MA" frameborder="0" width="640" marginwidth="0">Loading...</iframe> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4394476607717253925?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-89822864533530056602012-01-10T14:21:00.001-08:002012-01-10T14:29:21.832-08:00<p>Incrementalism can lead to good (in design) or bad (in politics) outcomes.&nbsp; Subtle changes to reports can often yield significant benefits.&nbsp; I hope I was able to achieve a positive experience with just a couple modifications to <a href="http://timelyportfolio.blogspot.com/2012/01/better-bullets.html" target="_blank">Better Bullets</a>. To achieve this result, please use the newest <a href="http://www.box.com/s/9jenb341qmv4iaoeh5uy" target="_blank">excelgrf_macros.xlsm</a>.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/tIdmubXBFPWgj8sxGMA7LdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-k2s3UCo9Bwc/Twy45BJ3UKI/AAAAAAACGVU/7Cl9Qxz4a0Y/s640/spark%252520bullet%252520even%252520better.png" width="640" height="411"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>I think the next version might take our formatting abilities a little too far, but I will show it just as another alternative.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/6See9MNhFZksrvEtPyKLpdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-QEPwrgK4XKQ/Twy7R_c69CI/AAAAAAACGVk/2jh6I_WpYeE/s640/spark%252520bullet%252520even%252520better%252520lots%252520of%252520colors.png" width="640" height="424"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>So far I have not heard any comments or suggestions.&nbsp; Please send them my way.&nbsp; I am aware that the instructions are fairly sparse. I hope to do a screencast very soon.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8982286453353005660?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-85245783773831958902012-01-09T14:41:00.001-08:002012-01-09T14:41:12.487-08:00<p>It has always been a dream of mine to incorporate R graphs and analysis in an Advent Axys report.&nbsp; The unbelievable work from the guys at Statconn <a title="http://rcom.univie.ac.at/" href="http://rcom.univie.ac.at/">http://rcom.univie.ac.at/</a> make this dream possible.&nbsp; If we use the same <a href="http://www.box.com/s/yhdagoqpznif8248etc5">perhstsp.rep</a> created for <a href="http://timelyportfolio.blogspot.com/2012/01/better-bullets.html">Better Bullets</a>, and then apply a little Excel macro magic <a title="http://www.box.com/s/9jenb341qmv4iaoeh5uy" href="http://www.box.com/s/9jenb341qmv4iaoeh5uy">excelgrf_macros.xlsm</a> with help from RExcel and PerformanceAnalytics, we can go from</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Wd8LHD8bIGsbgJpYldM5l9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-GK74jCyoE4E/TwtsLcFODeI/AAAAAAACGUs/dsndux5nZ08/s800/r%252520axys%252520step%2525201.png" width="453" height="494"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/JBI5OS7CMQbQeqsVi4zztNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-GGVUXeUkqro/TwtsMv7ZK_I/AAAAAAACGUw/Ozlq4cVzMhg/s800/r%252520axys%252520step%2525202.png" width="488" height="515"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>to</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/C_1PMK3hPCAZ937gRb7r-dMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-OQUJ1UKnQiM/TwtsLuXciiI/AAAAAAACGU8/bvXWr3maUaw/s640/r%252520axys%252520result.png" width="640" height="537"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>I never really expected to be able to accomplish this.&nbsp; Roll Tide!</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8524578377383195890?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-84454942756887931922012-01-09T07:26:00.001-08:002012-01-09T07:26:16.234-08:00<p>As I reread my <a href="http://timelyportfolio.blogspot.com/2012/01/fews-bullets-in-axys-reports.html">Few’s Bullets in Axys Reports</a> post, I think the better way to visualize this </p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/gdDy0sPXcnJVmhrHLMdmMNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-hiTDgnPrkxw/Twd4XGoeF-I/AAAAAAACGUE/s-AZg1-sYD8/s640/spark%252520result.png" width="640" height="347"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>would be to make the max the max from the entire series, so the scale is consistent.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/9f-VrOHjc430TMTMfx7YeNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-654LUbG3of4/TwsFpGRlt3I/AAAAAAACGUc/Y9pFXmKytIQ/s640/spark%252520bullet%252520improved.png" width="640" height="389"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>The very slightly changed Excel file with the new line of code is <a href="http://www.box.com/s/9jenb341qmv4iaoeh5uy">here</a>. Everything else is the same as <a href="http://timelyportfolio.blogspot.com/2012/01/fews-bullets-in-axys-reports.html">Few’s Bullets in Axys Reports</a>.</p> <p>As always, I love comments and suggestions.&nbsp; Please let me know your thoughts.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8445494275688793192?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-37411996391560250862012-01-06T14:42:00.001-08:002012-01-09T07:26:50.093-08:00<p>Just a couple of days ago, I would have said what I am about to show was impossible in Axys reports.&nbsp; However, with the very fine work from Fabrice Rimlinger <a title="http://sparklines-excel.blogspot.com/" href="http://sparklines-excel.blogspot.com/">http://sparklines-excel.blogspot.com/</a> and a little stretching of the boundaries, I have been able to get bullet performance graphs in an Axys performance report.&nbsp; For more on Stephen Few’s innovative bullet charts, see <a href="http://www.perceptualedge.com/blog/?p=217">http://www.perceptualedge.com/blog/?p=217</a> or for his books see</p><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=0970601999&amp;nou=1&amp;ref=qf_sp_asin_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=0596100167&amp;nou=1&amp;ref=qf_sp_asin_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe> <p>Just like in <a href="http://timelyportfolio.blogspot.com/2012/01/axys-combo-incremental-improvement.html">Axys Combo Incremental Improvement</a>, we will run a custom report (in this case an amended Axys perhist <a href="http://www.box.com/s/yhdagoqpznif8248etc5" target="_blank">perhstsp.rep</a>) and use <a title="http://www.box.com/s/ei1dqxpy1o20c6bs5gte" href="http://www.box.com/s/ei1dqxpy1o20c6bs5gte">excelgrf_macros.xlsm</a> to get our new macro sparkbullet.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/qyD-6tqkm7x6NiVR20ZlxtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-EZD2kX7UGnU/Twd4W8gOiII/AAAAAAACGT8/8OBbg6Q4j7M/s800/spark%252520bullet%252520step%2525201.png" width="437" height="517"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/HMfsg5lv5MKj-8ZTKFkArtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-IkyXdbU5gBI/Twd4XNlWd1I/AAAAAAACGUA/E4t73i7KOUY/s800/spark%252520bullet%252520step%2525202.png" width="353" height="358"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>And we get something amazing but not all that pretty.&nbsp; I’ll take it though.&nbsp; <em><font color="#9e7c7c">Please see the updated <a href="http://timelyportfolio.blogspot.com/2012/01/better-bullets.html">Better Bullets</a> for an even better version of this chart.</font></em></p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/gdDy0sPXcnJVmhrHLMdmMNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-hiTDgnPrkxw/Twd4XGoeF-I/AAAAAAACGUE/s-AZg1-sYD8/s640/spark%252520result.png" width="640" height="347"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-3741199639156025086?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-33289064480341323462012-01-06T10:03:00.001-08:002012-01-06T14:49:12.443-08:00<p>20 years of data is nowhere near enough to satisfy my insatiable appetite for bigger datasets.&nbsp; While I showed <a href="http://timelyportfolio.blogspot.com/2011/12/record-long-term-treasury-returns.html">Record Long Term Treasury Returns</a> with Vanguard’s US Long Treasury mutual fund, its 20 year life is not sufficient to give me comfort risking money.&nbsp; What happens when we take the Moody’s AAA rate series dating back to 1919?</p> <p>My opinion changes dramatically when I include 70 more years, and the opportunity is much less certain.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/kI_RO7b8Z_U75CXTyu-u_dMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-4arXH87qGlw/Twc1rIhtgpI/AAAAAAACGTs/duW4ZX5lqrI/s640/lattice.jpeg" width="640" height="607"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/oVZr9o18ENU01RIButsH7tMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-5a7Q-X0SXLc/Twc1rOwUoBI/AAAAAAACGTg/qi5m5tzmDl8/s640/scatter.jpeg" width="640" height="619"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/3AC_XssgX_ezB8gnoR9umdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-qyyeHN_JIEY/Twc1rAHoYbI/AAAAAAACGTc/XzUHTZ8KmtM/s640/dotplot.jpeg" width="640" height="619"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1572814">R code from GIST:</a></p><script src="https://gist.github.com/1572814.js?file=moodys%20aaa%20forward%20and%20back.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-3328906448034132346?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-2316254557538812072012-01-06T08:44:00.001-08:002012-01-06T08:44:00.880-08:00<p>I am sure most of my normal readers discovered a long time ago that I have no degree in graphic design, but that does not mean that I cannot try.&nbsp; To further the proof of concept and hopefully inspire some thought, here is an initial pass at graphic design on <a href="http://timelyportfolio.blogspot.com/2012/01/axys-combo-incremental-improvement.html">Axys Combo Incremental Improvement</a>.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/hXC6VVpMQg63hoLTZJjOptMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-cqFqIWqElLU/TwcjciCsHaI/AAAAAAACGTM/pl_3La5532Y/s640/actimval%252520graphic%252520design.png" width="640" height="353"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-231625455753881207?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-91064080644999578212012-01-05T20:46:00.001-08:002012-01-05T20:46:09.456-08:00<p>As I experiment more with <a href="http://timelyportfolio.blogspot.com/2012/01/power-of-sparklines-in-advent-axys.html">Power of Sparklines in Advent Axys</a>, I thought my first real challenge would be to get two charts with one report.&nbsp; In my mind, client reporting generally contains four major sections:</p> <ol> <ol> <li>Performance <li>Activity Summary <li>Historical Value <li>Allocation/Current Holdings</li></ol></ol> <p>For this incremental improvement, I will work on 2 (Activity Summary) and 3 (Historical Value).&nbsp; The new Excel file can be downloaded at <a title="http://www.box.com/s/ay4diedl0cq9ean02c89" href="http://www.box.com/s/ay4diedl0cq9ean02c89" target="_blank">excelgrf_macros.xlsm</a> and our fancy new Axys report at <a href="http://www.box.com/s/452cky1rizy10mhvjyia" target="_blank">actimval.rep</a>.&nbsp; I accept no credit for the code in the report since most comes from the standard Axys activity.rep and mval.rep.</p> <p>The steps will be very similar to those taken in <a href="http://timelyportfolio.blogspot.com/2012/01/power-of-sparklines-in-advent-axys.html">Power of Sparklines in Advent Axys</a>.</p> <p>First run actimval.rep in Axys reports.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/CM8WdmmNsHhYN-zqoaSvy9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-5atysPow7T4/TwZ7mOv8XcI/AAAAAAACGS4/1_As6l5ZBV8/s800/actimval%252520spark%252520step%2525201.png" width="602" height="79"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Then click graph</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/11efDYrHBaDTBAaCxlkL3tMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/--efC1sFmmig/TwZ7l0U0NLI/AAAAAAACGSk/irYj7MouixM/s800/actimval%252520spark%252520step%2525202.png" width="316" height="369"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>which brings up the second graph dialog box where we can input the location and name of the Excel file and our new macro.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/5v5eyyZ5IZvrllmk2UXG7NMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-ULdxL5saKe0/TwZ7mJRjQ9I/AAAAAAACGS0/NLDXZuUMnmc/s800/actimval%252520spark%252520step%2525203.png" width="397" height="384"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>And hopefully you will get something similar to this. Not pretty but certainly a step in the right direction.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/MJotxtPfDLXZOhpAA4_1CtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-bvKCOgsbCHU/TwZ7mGZW3WI/AAAAAAACGSo/fER1z_ayHaE/s640/actimval%252520spark%252520result.png" width="640" height="490"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Currently, most of this is more proof of concept and experimentation, but by the end of all this, I foresee some mighty clean and impressive report packages.&nbsp; Please comment and contribute.&nbsp; I know this is pretty domain specific, so let me know if you are out there.&nbsp; As far as I know the only folks professionally pursuing Axys custom reporting besides Advent are <a title="http://cssi.org/" href="http://cssi.org/">http://cssi.org/</a> and <a title="http://www.isitc.com/" href="http://www.isitc.com/">http://www.isitc.com/</a>.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-9106408064499957821?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-83007986709970790992012-01-03T13:11:00.001-08:002012-01-03T13:11:43.220-08:00<p>I recently discovered the amazing work of Fabrice Rimlinger at <a href="http://sparklines-excel.blogspot.com">http://sparklines-excel.blogspot.com</a> and thought of what I believe is a novel way of using the Microsoft Excel integration with Advent Axys reports to potentially achieve a dashboard style report.&nbsp; This would be far more visually compelling and informative than anything else I have seen in Axys.&nbsp; For this report, we will just use the standard Axys Portfolio Summary Report and then an Excel macro <a title="http://www.box.com/s/9jenb341qmv4iaoeh5uy" href="http://www.box.com/s/9jenb341qmv4iaoeh5uy">http://www.box.com/s/9jenb341qmv4iaoeh5uy</a>.&nbsp; Please also install the appropriate Excel add-in from <a href="http://sparklines-excel.blogspot.com">http://sparklines-excel.blogspot.com</a>.</p> <p><embed type="application/x-shockwave-flash" src="https://picasaweb.google.com/s/c/bin/slideshow.swf" width="600" height="400" flashvars="host=picasaweb.google.com&captions=1&noautoplay=1&hl=en_US&feat=flashalbum&RGB=0x000000&feed=https%3A%2F%2Fpicasaweb.google.com%2Fdata%2Ffeed%2Fapi%2Fuser%2Fkentonlrussell%2Falbumid%2F5693510787022099361%3Falt%3Drss%26kind%3Dphoto%26hl%3Den_US" pluginspage="http://www.macromedia.com/go/getflashplayer"></embed> <p>I know the audience for this will be more limited than my general audience.&nbsp; I might move these Axys report discussions to my incomplete and defunct <a href="http://axysreporting.com">http://axysreporting.com</a> site.</p> <p>For the R lover, I am hoping to also incorporate the unbelievable RExcel from <a title="http://rcom.univie.ac.at/" href="http://rcom.univie.ac.at/">http://rcom.univie.ac.at/</a>.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8300798670997079099?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-84418105839745195902011-12-21T08:11:00.001-08:002011-12-21T08:11:26.803-08:00<p>I mistakenly assume everyone knows that US Treasury Returns have been extreme in 2011.&nbsp; As we near the end of the year, I thought it would be beneficial to look at the world’s best performer while incorporating some new graphical techniques.&nbsp; There is also an opinion (NOT INVESTMENT ADVICE) expressed in one of the charts.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/P8TMOe1Agwqss92i0r2xL9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-1rUFpq07L98/TvIESCPQqaI/AAAAAAACDw8/jsKd63Qh1AU/s640/xyplot%252520of%252520forward%252520and%252520back.jpeg" width="639" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/ny5pWThWUn5PV9tz3Q87jdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-EH42HE6BDjw/TvIESDHRzkI/AAAAAAACDxA/A8Cec8yo-us/s640/scatter%252520plot%252520of%252520forward%252520and%252520back.jpeg" width="640" height="588"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1506532" target="_blank">R code in GIST:</a></p><script src="https://gist.github.com/1506532.js?file=vustx%20forward%20and%20back.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8441810583974519590?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-81090781669845188012011-12-16T13:07:00.001-08:002011-12-16T13:07:00.800-08:00<p>Since my fifth most popular post has been <a href="http://timelyportfolio.blogspot.com/2011/04/bond-market-as-casino-game-part-1.html">Bond Market as a Casino Game Part 1</a>, I thought I would use Vanguard Total US Bond Market mutual fund (VBMFX) monthly returns to build our skills in the lattice R package and help visualize the unbelievable run of U.S. bonds (<a href="Bonds Tumble and Questions Start Getting Asked" target="_blank">Calmar Ratio 1.37 over the past 20 years</a>).</p><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=0387759689&amp;nou=1&amp;ref=qf_sp_asin_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe> <p>Although I have primarily graphed with R base graphics, PerformanceAnalytics charts, and ggplot, the lattice package provides an extremely powerful set of charting tools.</p> <p>We can start with a basic qqplot of the entire set of monthly returns.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/CHgOTD7kSRjlnClX1mRoO9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-SHRbWuwsW34/TuuxtoNZS_I/AAAAAAACDwU/UVXlRow6mko/s640/vbmfx%252520basic%252520qqplot.jpeg" width="640" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Then, we can group by year.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/4NLnmxeZAUqvuY1jvFxcotMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-RIyigqXwPkc/TuuxtllEqbI/AAAAAAACDwg/Sw0WSg8_X0M/s640/vbmfx%252520qqplot%252520by%252520year.jpeg" width="640" height="557"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Or, we can also very easily split each year into its own panel.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/n7qWj6KgCSpH9Psgy6VGytMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-PBoHEbaCASw/TuuxtXE6LrI/AAAAAAACDwQ/fgKRQiSFq6I/s640/vbmfx%252520qqplot%252520panel%252520by%252520year.jpeg" width="640" height="615"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Here is a little different look with a density plot.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/tpAaSQ_xtF6x8v-Dfe0lD9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-M0pQm35jBQ0/Tuuxs71NqAI/AAAAAAACDwI/vZdslZIwK1U/s640/vbmfx%252520density%252520plot%252520by%252520year.jpeg" width="640" height="615"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Now let’s build boxplots and dotplots.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/VOjKcNrF5kYHZuqS6V-hI9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-s6gCAYC4PQM/TuuxsPTDuLI/AAAAAAACDv0/PmHWuRMEtno/s640/vbmfx%252520boxplot%252520by%252520year.jpeg" width="640" height="615"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Add an annual dotplot to a boxplot for the entire period.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/bpL5a3_Y6b21zla16E46pNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-xMNg80dVqpA/TuuxsTlvZ_I/AAAAAAACDwE/C0AHf0wgpng/s640/vbmfx%252520dotplot%252520with%252520boxplot%252520overlay.jpeg" width="626" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Or we can add a boxplot for each year.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/p3aiAPL5UDVmzkLfcCsnpdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-N6ppOIQEOFQ/TuuxsXj6kfI/AAAAAAACDv4/3Xeg4lsGB9c/s640/vbmfx%252520dotplot%252520with%252520yearly%252520boxplot%252520overlay.jpeg" width="626" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>See <a title="http://timelyportfolio.blogspot.com/search/label/bonds" href="http://timelyportfolio.blogspot.com/search/label/bonds">http://timelyportfolio.blogspot.com/search/label/bonds</a> for all my posts on bonds.</p> <p><a href="https://gist.github.com/1487949" target="_blank">R code from GIST:</a></p><script src="https://gist.github.com/1487949.js?file=lattice%20explore%20vbmfx.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8109078166984518801?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-32662748686532733252011-12-15T13:02:00.001-08:002011-12-15T13:02:43.443-08:00<p>A basic tenet in finance is that higher risk should lead to higher return as the time horizon stretches to infinity.&nbsp; However, in bonds, higher risk has not meant higher return with either credit risk (high-yield) or long duration risk (maturity &gt; 15 years).&nbsp; Based on some quick analysis of <a href="http://mba.tuck.dartmouth.edu/pages/faculty/ken.french" target="_blank">Kenneth French’s dataset</a> on returns by market capitalization, it appears theory might better explain reality but not in a linear fashion.&nbsp; For those more interested in risk and return on small caps, see this fascinating revelation refuting a basic tenet of finance <a href="http://systematicrelativestrength.com/2011/12/01/about-that-small-cap-effect-oops/">About That Small Cap Effect: Oops!</p> <p></a></p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/aoO_4wK4oLFEQdPUMM_CkdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-XgNurWlwuAw/TupfFBwOMzI/AAAAAAACDvU/jlV4-STX4GM/s800/size%252520risk%252520return.jpeg" width="624" height="624"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/K9e-2Wq-Q99JAKzczVWdbtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-BimXgP83TUg/TupfFJKhpVI/AAAAAAACDvk/XaSAmCOm0zI/s800/size%252520frontier.jpeg" width="624" height="624"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Uzz36gMh60bkDeWKIx20itMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-cHu8PKBrn9M/TupfFOfE_6I/AAAAAAACDvY/WkGTjvPrCjw/s800/size%252520correlation.jpeg" width="624" height="624"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1482847" target="_blank">R code from GIST:</a></p><script src="https://gist.github.com/1482847.js?file=size%20risk%20return.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-3266274868653273325?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-47342934256416479942011-12-09T10:04:00.001-08:002011-12-09T11:16:19.123-08:00<p>In a follow up to <a href="http://timelyportfolio.blogspot.com/2011/11/evolving-domestic-frontier.html">Evolving Domestic Frontier</a>, I wanted to explore the efficient frontier including international indexes since 1980.&nbsp; Life is great when your primary indexes (Barclays Aggregate and S&amp;P 500) lie on the frontier as they did 1980-1999.&nbsp; The situation becomes much more difficult with a frontier like 2000-now.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Qx3XL3avReOxgfDN8LBtltMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-iJuhaI9YxFg/TuJCYUamkxI/AAAAAAACDuo/yByXIqytQls/s640/two%252520frontiers.jpeg" width="624" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>If we examine return, risk, and Sharpe though, 1980 to now was really not that bad with annualized returns of all indexes stocks and bonds &gt; 8% even including the last decade of “equity misery”.&nbsp; As the S&amp;P 500 shifted from the top of the efficient frontier to the bottom, it seems the focus over the last decade as been finding alternatives for the S&amp;P 500. Strangely, the unbelievable riskless return of bonds has allowed some investors to claim and use bonds as one of these potential alternatives to the S&amp;P 500.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/4vyxse9OW9STNj8TTckcctMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-hBvmwiKXW1o/TuJCXl_fTiI/AAAAAAACDuY/O_V7uxPjJMo/s640/return%252520risk%252520sharpe.jpeg" width="640" height="626"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/E7Wsu8eGJb8uAixA9P2PCdMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-hlThHFPA5YY/TuJCXgX0pCI/AAAAAAACDuk/UWVJHSt4nvU/s640/ggplot%252520return%252520risk%252520sharpe.jpeg" width="640" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Bonds as alternatives to equities have made even more sense when we look at correlations.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/h2b7hgQFJzFppcJawMF_NNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-00egXf_5558/TuJCXgT9xGI/AAAAAAACDuU/I-gU71C7bmk/s640/correlation%252520by%252520period.jpeg" width="624" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>However, bonds based on the yield to maturity of the Barclays Aggregate index suggest, even guarantee, forward returns of only 2.3%, significantly below the +8% generously provided for 30 years.&nbsp; I believe the focus on alternatives should be alternatives for the guaranteed miserably low returns of bonds (<a href="http://online.wsj.com/article/SB10001424052970204449804577068152764286924.html" target="_blank">WSJ Bond Buyers Dilemma</a>).&nbsp; The trick though is reducing risk (drawdown) of these alternatives to an acceptable level to most bond investors.&nbsp; Max drawdown on bonds since 1982 has been 5%, which is virtually an impossible constraint for any risky alternatives, since in even very attractive secular buy-hold periods, drawdown generally is 20% to 30%.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/xfhcYpZh52GoJRg6o_mO-tMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-p3XT9bi3ivA/TuJJl0GBSKI/AAAAAAACDu8/HzLK7DiRkE0/s640/drawdown%252520bond.jpeg" width="640" height="632"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Our options are basically limited to cash, which at 0% return is unacceptable, unless we can discover a method to reduce drawdown on the risky set of alternatives to 20%, but really down to 10%.&nbsp; How do we transform risky alternatives with historical drawdowns of 40%-70% to an acceptable bond alternative?&nbsp; I think it requires tactical techniques blended with cash with a lot of client education and hand-holding.</p> <p><a href="https://gist.github.com/1452451" target="_blank">R code from GIST</a>:</p><script src="https://gist.github.com/1452451.js?file=taleoftwo.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4734293425641647994?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-2098869648093194382011-12-07T19:23:00.001-08:002011-12-07T19:23:05.835-08:00<p>December 8, 2010, I sat down to write my first post on Timely Portfolio <a href="http://timelyportfolio.blogspot.com/2010/12/reading.html">Reading-&gt;Writing</a></p> <blockquote> <p>“I am determined to play not spectate. After 20 years of voracious reading, I have decided to write, and this blog represents my commitment. More than likely it will be a reflection of me, so a lot about my work/passion money management and markets but also hopefully some worthwhile thoughts and observations. I will be the writer and possibly the only reader ultimately but I know that I will benefit immensely from this project. Any benefit to others will be extremely gratifying and help resolve my debt to all the wonderful authors that have entertained and enlightened me over the years.”</p></blockquote> <p>After a couple of months, I was able to more specifically assess the benefit of my blogging in <a href="http://timelyportfolio.blogspot.com/2011/03/why-talk-my-book.html">Why Talk My Book?</a> <blockquote> <p>“…I blog to <blockquote> <p>1) record my thoughts with a timestamp and no benefit of hindsight <p>2) improve the thoroughness of my thoughts through the <a href="http://en.wikipedia.org/wiki/Hawthorne_effect">Hawthorne Effect</a>. If I publish something for all the world to see, I am going to make absolute sure that my references are correct. <p>3) get feedback to improve my thoughts. Please criticize and bash what I write. The markets hurt my feelings all the time and do far more damage than your thoughts ever will. Please share them.</p></blockquote> <p>Markets have humbled me far too greatly to believe that I can or will move markets. Only the established trend of the market can attract enough attention to move the market meaningfully in my favor. Markets are not efficient, and I have no private information. I simply need to be an diligent, honest, and humble observer of the market, and I will do well.”</p></blockquote> <p>The year in blogging has been incredibly fun, challenging, and educational.&nbsp; Thanks to all those who have joined me along the way, especially those that helped, commented, criticized, referred, and improved my blog.&nbsp; I never planned for or even imagined anything close to the stats shown below.</p> <p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/sDw1m8Ul23dS7i3QCUnBOtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-9xJNTpZrNRM/TuAqJ3Ze_aI/AAAAAAACDuA/KtSVw70aLg0/s800/first%252520year%252520stats.png" width="686" height="568"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table></p> <p>I love the interaction, so please let me know what you are thinking.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-209886964809319438?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com3tag:blogger.com,1999:blog-7630810606654250077.post-31690103123217284622011-12-06T19:43:00.001-08:002011-12-07T19:01:23.475-08:00<p>For a client meeting, I struggled with how best to illustrate world markets since June 2008.&nbsp; I used R to produce this (<em>I amended this post to reflect a prettier forked version as discussed in the comments)</em>, but I’m still not completely satisfied. Anyone have suggestions to improve?</p> <table style="width:auto;"><tr><td><a href="https://picasaweb.google.com/lh/photo/x0Yu4VkVxXLXn4OtCAcPetMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-Zn5jdsAaZAc/Tt_Ltbk7nNI/AAAAAAACDto/h6-w6spO3xM/s640/world%252520indexes%252520forked.jpg" height="640" width="520" /></a></td></tr><tr><td style="font-family:arial,sans-serif; font-size:11px; text-align:right">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&feat=embedwebsite">TimelyPortfolio</a></td></tr></table> <p>What I thought was interesting was US equity outperformance and the US 10y yield move through the financial collapse low 2.15% seen in December 2008 and significantly lower than the 2.87% at the S&amp;P low March 2009.&nbsp; I think both can be explained by an illusion of control assigned to the US.&nbsp; This illusion begins to unravel if the political process fails and monetary policy has reached its limits.</p> <p><a href="https://gist.github.com/1441322" target="_blank">R code from Gist:</a></p><script src="https://gist.github.com/1441322.js?file=world%20indexes%20since%202008-06.r"></script><div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-3169010312321728462?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com4tag:blogger.com,1999:blog-7630810606654250077.post-43797281354473343172011-12-04T13:03:00.001-08:002011-12-07T12:44:49.407-08:00<p><em>I have been notified by the authors that the code does not perfectly reflect the improved moving average introduced.&nbsp; In another post, I will explore the differences.&nbsp; The authors have now released their version of the code <a title="http://www.quantf.com/fotis-papailias/improved-moving-average-code-is-available-for-download/332" href="http://www.quantf.com/fotis-papailias/improved-moving-average-code-is-available-for-download/332">http://www.quantf.com/fotis-papailias/improved-moving-average-code-is-available-for-download/332</a>.</em></p> <p>When <a href="http://twitter.com/#!/quantfblog" target="_blank">@quantfblog</a> started following me on Twitter, I was delighted to discover their papers</p> <blockquote> <p><a href="http://ssrn.com/abstract=1926376" target="_blank">Papailias, Fotis and Thomakos, Dimitrios D., An Improved Moving Average Technical Trading Rule (September 11, 2011). Available at SSRN: http://ssrn.com/abstract=1926376</a></p> <p><a href="http://ssrn.com/abstract=1958906" target="_blank">Papailias, Fotis and Thomakos, Dimitrios D., An Improved Moving Average Technical Trading Rule II - Can We Obtain Performance Improvements with Short Sales? (November 12, 2011). Available at SSRN: http://ssrn.com/abstract=1958906</a></p></blockquote> <p>backed by a nice and improving website <a href="http://www.quantf.com">http://www.quantf.com</a>.&nbsp; I just could not resist the opportunity to port their improved moving average idea to R and run some additional tests.&nbsp; The entire process was extremely pleasant due to the authors’ willingness to test, comment, and suggest throughout the implementation process.&nbsp; Thanks so much to them for all their help.</p> <p>In this process, I AM NOT OFFERING INVESTMENT ADVICE.&nbsp; THIS IS SIMPLY A TEST/ILLUSTRATION.&nbsp; PURSUING THESE CONCEPTS WILL MOST LIKELY LOSE SIGNIFICANT AMOUNTS (ALL) OF YOUR MONEY.</p> <p>&nbsp;</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/D5x1LaXa_RrhVgEOYIJubNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-7LEv0HaQVOE/TtvdpSWAjCI/AAAAAAACDsw/Orm5zaGEm00/s640/performance%252520summary.jpg" width="500" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Li8B53U6YEKPhPlTbFbGuNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-Vjf4AyOcevU/Ttvdo9EAPUI/AAAAAAACDss/UJsuwKo-QGk/s640/ggplot%252520capm.jpg" width="500" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/zUElGTjwwO-DrA1UHcb6XNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-6jFYXw5NaNY/Ttvdol9EgcI/AAAAAAACDsc/PXRRsaJUbe0/s640/ggplot%252520downside.jpg" width="500" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>For fun, I thought it would be interesting to compare the "Improved Moving Average" to a <a href="http://mebanefaber.com" target="_blank">Mebane Faber</a> style 10-month moving average system.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/CINjZq08lYMK9HTlRSZ4-9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-3tsSh_u_yx4/Ttvdo_wTMaI/AAAAAAACDsg/AuMRVEmmMjs/s640/performance%252520monthly.jpg" width="500" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>&nbsp;</p> <p>While I enjoyed the testing, I am still not entirely sure if the “improved moving average” is significantly improved, but it certainly might fit someone’s utility curve better than the standard moving average.&nbsp; More than anything, this process has proven to me a couple of things:</p> <blockquote> <p>1) the beauty of open-source and collaboration.&nbsp; The authors were incredibly generous and helpful as I worked through this process.&nbsp; To even better demonstrate the power of open-source, I will use ttrTests to do additional testing and then the bt examples from <a href="http://systematicinvestor.wordpress.com">http://systematicinvestor.wordpress.com</a> in future posts.</p> <p>2) how even a simple moving average can become incredibly complex.&nbsp; Making one very slight change markedly changes the results.</p></blockquote> <p><a href="https://gist.github.com/1405561" target="_blank">R code from GIST:</a></p> <p>&nbsp;</p><script src="https://gist.github.com/1405561.js?file=MAImp.test.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4379728135447334317?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-86914077995478538992011-12-01T10:34:00.001-08:002011-12-01T10:39:13.586-08:00<p>In all my system development, I still have not been able to determine what universal underlying conditions significantly improve a system’s chances of outperforming buy-and-hold.&nbsp; Also, I have found very little discussion, so maybe R with some help from ttrTests can help answer my question of when I should just go buy-and-hold (a very pleasant situation for a money manager).&nbsp; Starting in this business in 1998, I have often said that I dream of a day when I can just buy and hold similar to Japan stocks 1980-1990, US stocks 1990-2000, and US bonds 1982-now.</p> <p>Those who follow my blog or know me already understand my obsession with drawdown, but that obsession focuses more on client/manager psychology <a href="http://ssrn.com/abstract=1958258" target="_blank">(Investing for the Long Run)</a> rather than drawdown’s effects on tactical systems.&nbsp; I do not understand the industry’s focus on standard deviation.&nbsp; I have never had a client call me or even worse fire me because my standard deviation has increased.&nbsp; I know the argument is that higher standard deviations lead to higher drawdown, but as I show later in the post, this does not seem to be the case.</p> <p><a href="http://www.advisorbenchmarking.com/" target="_blank"><img alt="" src="http://media.advisorone.com/advisorone/article/2011/07/14/PEChart2_Jul1411.jpg" width="400"></a></p> <p>Clients call me or fire me because they have lost money, so if I can minimize the frequency, amplitude, and duration of drawdowns, then I can help/guide the client and reduce the worry, which is one main reason why they are paying me.&nbsp; Also, though I think that focusing on minimizing drawdown can meaningfully increase the chances of achieving their long term return objectives (<a href="http://timelyportfolio.blogspot.com/2011/07/drawdown-control-can-also-determine.html">Drawdown Control Can Also Determine Ending Wealth</a> and <a title="Confidence, Ending Equity, and What I Can Do as the Money Manager" href="http://timelyportfolio.blogspot.com/2011/06/confidence-ending-equity-and-what-i-can.html">Confidence, Ending Equity, and What I Can Do as the Money Manager</a>), which is even more likely the reason why clients pay me.</p> <p>How nice would it be if drawdown also determines an objective system’s success?&nbsp; To start the testing I thought I would use the fine work of <a href="http://www.math.uic.edu/mslc/?sid=profile&amp;unid=dstjoh2" target="_blank">David St. John</a> on ttrTests (<a href="http://timelyportfolio.blogspot.com/2011/10/ttrtests-4th-and-final-test.html">ttrTests 4th and Final Test</a>) to get 100,000 bootstrapped samples from monthly S&amp;P 500 data to examine drawdown, standard deviation, skewness, and compound returns on buy-and-hold versus a <a href="http://www.mebanefaber.com" target="_blank">Mebane Faber 10-month moving average system</a>.&nbsp; Since I am so biased, I will let you determine the significance of drawdown on the results.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Cm3NzNSJf6tfPd84_nhwMtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-ii9gCoXBEiw/TtfE6jaqHlI/AAAAAAACDaQ/JEWJa_otsdA/s800/boxplots.jpeg" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/OR71ny65FxElclVjzSVHzNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-C5oMmppV3C0/TtfE6izwLEI/AAAAAAACDaU/N5V03a2Ndhk/s800/density%252520plots.jpeg" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Here is where I get some confidence in my belief higher standard deviation does not necessarily cause worse drawdowns. However, it is interesting that higher standard deviation has as high a correlation as drawdown with system out(under)performance (bottom right).</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/oHeUL-OAwih6NiHenpi1f9MTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-3Cyjo3TXBnQ/TtfE7CZax8I/AAAAAAACDac/O22DCpFG1lc/s800/correlation.jpeg" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://gist.github.com/1418765" target="_blank">R code from GIST:</a></p><script src="https://gist.github.com/1418765.js?file=drawdown%20and%20system%20success.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8691407799547853899?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-49243026315512545212011-12-01T08:07:00.001-08:002011-12-01T08:31:40.669-08:00<p>I think Satyajit Das’ guest post</p> <blockquote> <h4><a href="http://www.ritholtz.com/blog/2011/12/the-sovereign-debt-train-wreck-us-debt-is-still-a-problem/">The Sovereign Debt Train Wreck </a><br>from The Big Picture by Barry Ritholtz</h4></blockquote> <p>does a very nice job highlighting and clarifying some of my thoughts on the U.S. sovereign debt problem, which is clearly not being priced with a US 10y Treasury at 2.10% or even 4%.&nbsp; For those of you unfamiliar with Satyajit Das, his book exposed ex-ante both what caused the financial panic of 2008-2009 and the concurrent disgusting practices prevalent in finance.</p><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=0273731963&amp;nou=1&amp;ref=qf_sp_asin_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe> <p>For my thoughts on death spiral and the generosity of Asian central banks, see posts</p> <blockquote> <p><a href="http://timelyportfolio.blogspot.com/2011/10/generosity-of-asian-central-banks.html">Generosity of Asian Central Banks</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/03/death-spiral-of-country.html">Death Spiral of a Country</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/03/death-spiral-warning-graph.html">Death Spiral Warning Graph</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/03/unsustainable-gift.html">Unsustainable Gift</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/03/nine-lives-of-fed-put.html">Nine Lives of the Fed Put</a></p></blockquote><div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4924302631551254521?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-65390014015554898602011-11-22T20:23:00.001-08:002011-11-22T20:23:15.057-08:00<p>In lots of previous posts, I have demonstrated how to use the wonderful and free <a href="http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html" target="_blank">Kenneth French data</a> in R, but I have not shown a basic risk/return plot by size/momentum and industry.&nbsp; Hopefully, it will just be another example that somebody somewhere will find useful.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/K9RZdcx-vqrcPBnG3yCKmtMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-ozW9qtu18MI/Tsx0fLrTl2I/AAAAAAACCSA/Kjjq8JcD4bY/s800/risk%252520return%252520french%252520momentum.jpeg" width="553" height="552"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/C-Foc2zLIDMPCsTR3zuslNMTjNZETYmyPJy0liipFm0?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-bJ3vTpLRIJ8/Tsx0fbeDNXI/AAAAAAACCSE/-2Iqp5DQ2tU/s800/risk%252520return%252520french%252520industry.jpeg" width="553" height="552"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>R code in GIST:</p><script src="https://gist.github.com/1387885.js?file=french%20risk%20return.r"></script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-6539001401555489860?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-20248829209988029672011-11-22T13:52:00.001-08:002011-11-22T13:52:57.482-08:00<p>In search of better ways to post my R code, I finally discovered how GIST can help make my R blogging easier.&nbsp; I know I am way behind, and I apologize to my loyal readers for my shortcomings.&nbsp; Here is yesterday’s <a href="http://timelyportfolio.blogspot.com/2011/11/i-have-marveled-at-magical-russell-2000.html">Magical Russell 2000</a> code using GIST:</p><script src="https://gist.github.com/1387105.js"> </script> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2024882920998802967?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-25360761458978556342011-11-21T07:18:00.001-08:002011-11-21T07:18:38.363-08:00<p>I have marveled at the magical Russell 2000 in <a href="http://timelyportfolio.blogspot.com/2011/07/crazy-rut.html">Crazy RUT</a>, but I am still surprised at its behavior through this selloff.&nbsp; With a 20-day move of 30% (6% in one hour) and big outperformance to the developed and developing world, the Russell 2000 continues its magical display.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/IWq1HX51e8tXVq9ImGttvg?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-qIjmG2bBEes/TsprZ9OXnkI/AAAAAAACCRs/6j0Fh2O02hc/s640/distance%252520from%252520min%252520rut%252520and%252520w2dow.jpeg" width="640" height="579"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>R code:</p> <p>#look at distance from the 3 month minimum<br>#to compare the magical US Russell 2000<br>#to the world</p> <p>require(quantmod)</p> <p>tkrs &lt;- c("^W2DOW","^RUT")</p> <p>getSymbols(tkrs,from="1896-01-01",to=Sys.Date())</p> <p>#merge the closing values<br>markets &lt;- na.omit(merge(W2DOW[,4],RUT[,4]))</p> <p>#this is ugly but it works<br>altitude &lt;- function(x) x/min(x)-1<br>mins &lt;- as.xts(apply(markets[(NROW(markets)-250):NROW(markets),1:2],<br>&nbsp;&nbsp;&nbsp; MARGIN=2,FUN=<br>&nbsp;&nbsp;&nbsp; altitude))<br>plot.zoo(mins,screens=1,<br>&nbsp;&nbsp;&nbsp; col=c("cadetblue4","darkolivegreen3"),<br>&nbsp;&nbsp;&nbsp; lwd=2,ylab="% from 250 day minimum",xlab=NA,<br>&nbsp;&nbsp;&nbsp; main="Russell 2000 and DJ World ex US<br>&nbsp;&nbsp;&nbsp; Distance from 250 Day Minimum")<br>legend("bottom",c("DJ World ex US","Russell 2000"),lty=1,lwd=2,<br>&nbsp;&nbsp;&nbsp; col=c("cadetblue4","darkolivegreen3"),horiz=TRUE)</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2536076145897855634?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-57339820753039714452011-11-20T13:36:00.001-08:002011-11-20T13:36:01.760-08:00<p>After reading the fine article <a href="http://systematicinvestor.wordpress.com/2011/11/18/style-analysis/" target="_blank">Style Analysis from Systematic Investor</a> and <a href="http://www.asymmetricinvestmentreturns.com/asymmetric-investment-returns/what-we-can-learn-from-bill-miller-and-the-legg-mason-value-trust/" target="_blank">What we can learn from Bill Miller and the Legg Mason Value Trust from Asymmetric Investment Returns</a>, I thought I should combine the two in R with the FactorAnalytics package.&nbsp; Let’s explore the Legg Mason Value Trust run by Bill Miller to get some insight into the source of his returns over many years by using the Ken French momentum by size data set as factors.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/4I5qTnrLfvVP4AK3ETMUcw?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-4ve2gj6rPII/TsllQJZ_gSI/AAAAAAACCRY/RWTA0fz8_3k/s800/rolling%252520weights.jpeg" width="677" height="592"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/QC-w43NHtjB_fHzFWI0oCQ?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-WG0Dv1Pzu2I/TsllQIlkF6I/AAAAAAACCRI/5FWgKFGwBAw/s800/cumulative%252520weights.jpeg" width="553" height="552"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/0aZlOat6z7W_vtPh_SjhGw?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-AQxYFv9beDI/TsllQabI6FI/AAAAAAACCRM/UKvWPS9Av_o/s800/rolling%252520R.jpeg" width="677" height="592"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/open?id=0B2qp2r96khJPOTIzYjIxYzUtMDI0Ni00ZTllLTk4NzItY2VkNWM1MmNlMjZm" target="_blank">R code (click to download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><span style="font-style: italic; color: #666666">#use Ken French momentum style indexes for style analysis</span><br /><span style="font-style: italic; color: #666666">#http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/6_Portfolios_ME_Prior_12_2.zip</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span>FactorAnalytics<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; my.url=<span style="color: #0000ff">"http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/6_Portfolios_ME_Prior_12_2.zip"</span><br />my.tempfile<span>&lt;-</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"<span style="color: #000099; font-weight: bold">\\</span>frenchmomentum.zip"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><br />my.usefile<span>&lt;-</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"<span style="color: #000099; font-weight: bold">\\</span>6_Portfolios_ME_Prior_12_2.txt"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/utils/download.file"><span style="color: #003399; font-weight: bold">download.file</span></a><span style="color: #009900">(</span>my.url<span style="color: #339933">,</span> my.tempfile<span style="color: #339933">,</span> method=<span style="color: #0000ff">"auto"</span><span style="color: #339933">,</span> <br /> quiet = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/mode"><span style="color: #003399; font-weight: bold">mode</span></a> = <span style="color: #0000ff">"wb"</span><span style="color: #339933">,</span>cacheOK = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/utils/unzip"><span style="color: #003399; font-weight: bold">unzip</span></a><span style="color: #009900">(</span>my.tempfile<span style="color: #339933">,</span>exdir=<a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span>junkpath=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#read space delimited text file extracted from zip</span><br />french_momentum <span>&lt;-</span> <a href="http://inside-r.org/r-doc/utils/read.table"><span style="color: #003399; font-weight: bold">read.table</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a>=my.usefile<span style="color: #339933">,</span><br /> header = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> sep = <span style="color: #0000ff">""</span><span style="color: #339933">,</span><br /> as.is = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span><br /> skip = <span style="color: #cc66cc">12</span><span style="color: #339933">,</span> nrows=<span style="color: #cc66cc">1017</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>french_momentum<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Small"</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>french_momentum<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">"."</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Large"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>french_momentum<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">"."</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get dates ready for xts index</span><br />datestoformat <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>french_momentum<span style="color: #009900">)</span><br />datestoformat <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"01"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">"-"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get xts for analysis</span><br />french_momentum_xts <span>&lt;-</span> as.xts<span style="color: #009900">(</span>french_momentum<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">6</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> order.by=<a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; french_momentum_xts <span>&lt;-</span> french_momentum_xts<span>/</span><span style="color: #cc66cc">100</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get price series from monthly returns</span><br />french_price<span>&lt;-</span>as.xts<span style="color: #009900">(</span><br /> <a href="http://inside-r.org/r-doc/base/apply"><span style="color: #003399; font-weight: bold">apply</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>+</span>coredata<span style="color: #009900">(</span>french_momentum_xts<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">6</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span>MARGIN=<span style="color: #cc66cc">2</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/cumprod"><span style="color: #003399; font-weight: bold">cumprod</span></a><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> index<span style="color: #009900">(</span>french_momentum_xts<span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#check data for reasonability</span><br />plot.zoo<span style="color: #009900">(</span>french_price<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/log"><span style="color: #003399; font-weight: bold">log</span></a>=<span style="color: #0000ff">"y"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#for this example let's use Bill Miller's fund</span><br />getSymbols<span style="color: #009900">(</span><span style="color: #0000ff">"LMVTX"</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span> to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span> adjust=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #009900">)</span><br />LMVTX <span>&lt;-</span> to.monthly<span style="color: #009900">(</span>LMVTX<span style="color: #009900">)</span><br />index<span style="color: #009900">(</span>LMVTX<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/format"><span style="color: #003399; font-weight: bold">format</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>index<span style="color: #009900">(</span>LMVTX<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"%Y-%m-01"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />LMVTX.roc <span>&lt;-</span> ROC<span style="color: #009900">(</span>LMVTX<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span>&nbsp;&nbsp; perfComp <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/na.omit"><span style="color: #003399; font-weight: bold">na.omit</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>LMVTX.roc<span style="color: #339933">,</span>french_momentum_xts<span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; chart.RollingStyle<span style="color: #009900">(</span>perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> width=<span style="color: #cc66cc">36</span><span style="color: #339933">,</span><br /> colorset=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"darkseagreen1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkseagreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkseagreen4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"slateblue1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"slateblue3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"slateblue4"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"LMVTX Rolling 36mo French Momentum Weights"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#could use the packaged chart.Style but does not allow the</span><br /><span style="font-style: italic; color: #666666">#flexibility I would like</span><br /><span style="font-style: italic; color: #666666">#chart.Style(perfComp[,1],perfComp[,2:NCOL(perfComp)],</span><br /><span style="font-style: italic; color: #666666"># colorset=c("darkseagreen1","darkseagreen3","darkseagreen4","slateblue1","slateblue3","slateblue4"),</span><br /><span style="font-style: italic; color: #666666"># main="LMVTX French Momentum Weights")</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get weights for the cumulative period</span><br />style.weight <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.matrix"><span style="color: #003399; font-weight: bold">as.matrix</span></a><span style="color: #009900">(</span>style.fit<span style="color: #009900">(</span>perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span>$</span>weights<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/barplot"><span style="color: #003399; font-weight: bold">barplot</span></a><span style="color: #009900">(</span>style.weight<span style="color: #339933">,</span>beside=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span>ylim=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/max"><span style="color: #003399; font-weight: bold">max</span></a><span style="color: #009900">(</span>style.weight<span style="color: #009900">)</span><span>+</span><span style="color: #cc66cc">0.2</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> names.arg=<a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>style.weight<span style="color: #009900">)</span><span style="color: #339933">,</span>cex.names=<span style="color: #cc66cc">0.7</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"darkseagreen1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkseagreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkseagreen4"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"slateblue1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"slateblue3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"slateblue4"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"LMVTX French Momentum Weights<br /> Since "</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/format"><span style="color: #003399; font-weight: bold">format</span></a><span style="color: #009900">(</span>index<span style="color: #009900">(</span>LMVTX<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">"%b %Y"</span><span style="color: #009900">)</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#look at total R to determine goodness of fit</span><br />style.R <span>&lt;-</span> style.fit<span style="color: #009900">(</span>perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> perfComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span>$</span>R.squared&nbsp;&nbsp;&nbsp;&nbsp; styleR <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/function"><span style="color: #003399; font-weight: bold">function</span></a><span style="color: #009900">(</span>x<span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <a href="http://inside-r.org/r-doc/base/as.numeric"><span style="color: #003399; font-weight: bold">as.numeric</span></a><span style="color: #009900">(</span>style.fit<span style="color: #009900">(</span>R.fund=x<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/drop"><span style="color: #003399; font-weight: bold">drop</span></a>=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">]</span><span style="color: #339933">,</span>R.style=x<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>x<span style="color: #009900">)</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/drop"><span style="color: #003399; font-weight: bold">drop</span></a>=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">]</span><span style="color: #339933">,</span>method=<span style="color: #0000ff">"constrained"</span><span style="color: #339933">,</span>selection=<span style="color: #0000ff">"none"</span><span style="color: #339933">,</span>leverage=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">)</span><span>$</span>R.squared<span style="color: #009900">)</span><br /><span style="color: #009900">}</span><br /><span style="font-style: italic; color: #666666">#convert to matrix since I get</span><br /><span style="font-style: italic; color: #666666">#error "The data cannot be converted into a time series."</span><br /><span style="font-style: italic; color: #666666">#when I use xts as data</span><br />style.RollingR <span>&lt;-</span> as.xts<span style="color: #009900">(</span>rollapply<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/utils/data"><span style="color: #003399; font-weight: bold">data</span></a>=<a href="http://inside-r.org/r-doc/base/as.matrix"><span style="color: #003399; font-weight: bold">as.matrix</span></a><span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #339933">,</span><br /> width=<span style="color: #cc66cc">12</span><span style="color: #339933">,</span>FUN=styleR<span style="color: #339933">,</span>by.column=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/by"><span style="color: #003399; font-weight: bold">by</span></a>=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> order.by=index<span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">12</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>perfComp<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br />chart.TimeSeries<span style="color: #009900">(</span>style.RollingR<span style="color: #339933">,</span>ylab=<span style="color: #0000ff">"Rolling 12-mo R"</span><span style="color: #339933">,</span><br /> main=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"LMVTX Rolling R versus French Momentum<br /> Since "</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/format"><span style="color: #003399; font-weight: bold">format</span></a><span style="color: #009900">(</span>index<span style="color: #009900">(</span>LMVTX<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">"%b %Y"</span><span style="color: #009900">)</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>h=style.R<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span>x=<span style="color: #cc66cc">1</span><span style="color: #339933">,</span>y=style.R<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/labels"><span style="color: #003399; font-weight: bold">labels</span></a>=<span style="color: #0000ff">"r for entire series"</span><span style="color: #339933">,</span>adj=<span style="color: #cc66cc">0</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred"</span><span style="color: #009900">)</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-5733982075303971445?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-56505999823123367192011-11-18T13:39:00.001-08:002011-11-18T13:39:04.951-08:00<p>THIS IS NOT INVESTMENT ADVICE AND WILL PROBABLY WIPE OUT ALL YOUR MONEY IF PURSUED.&nbsp; While exploring utilities, I discovered a strange phenomenon that I have not quite thoroughly understood, but I attribute to the business cycle.&nbsp; If I dust off the system proposed in <a href="http://timelyportfolio.blogspot.com/2011/08/unrequited-lm-love.html">Unrequited lm Love</a>, apply that signal to utilities as my total entry/exit, and then use relative strength to decide utilities or transports (really all cyclicals work with chemicals best), I get some magic. This is much longer than my normal simple process but I think the result might be worth the effort.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/LdsDrjop_U_a1DJ1w_WvZQ?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-V5o7313SAZ4/TsbPVEhPqvI/AAAAAAACCQ0/niwJtxsk1fI/s640/performance%252520summary.jpg" width="500" height="640"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Although I use the <a href="http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html">Kenneth French data set (thanks again)</a>, the method works very similarly on the Dow Jones series easily obtained through getSymbols with Yahoo! Finance or FRED.</p> <p><a href="https://docs.google.com/open?id=0B2qp2r96khJPMzhjYmE1NmYtOGVlYy00YTA4LWEzY2QtZGJiODg1Y2QxOGY4">Sloppy R code (Click to Download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><span style="font-style: italic; color: #666666">#get very helpful Ken French data</span><br /><span style="font-style: italic; color: #666666">#for this project we will look at Industry Portfolios</span><br /><span style="font-style: italic; color: #666666">#http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/17_Industry_Portfolios.zip</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/RColorBrewer"><span>RColorBrewer</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#my.url will be the location of the zip file with the data</span><br />my.url=<span style="color: #0000ff">"http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/17_Industry_Portfolios.zip"</span><br /><span style="font-style: italic; color: #666666">#this will be the temp file set up for the zip file</span><br />my.tempfile<span>&lt;-</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"<span style="color: #000099; font-weight: bold">\\</span>frenchindustry.zip"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#my.usefile is the name of the txt file with the data</span><br />my.usefile<span>&lt;-</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"<span style="color: #000099; font-weight: bold">\\</span>17_Industry_Portfolios.txt"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/utils/download.file"><span style="color: #003399; font-weight: bold">download.file</span></a><span style="color: #009900">(</span>my.url<span style="color: #339933">,</span> my.tempfile<span style="color: #339933">,</span> method=<span style="color: #0000ff">"auto"</span><span style="color: #339933">,</span> <br /> quiet = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/mode"><span style="color: #003399; font-weight: bold">mode</span></a> = <span style="color: #0000ff">"wb"</span><span style="color: #339933">,</span>cacheOK = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/utils/unzip"><span style="color: #003399; font-weight: bold">unzip</span></a><span style="color: #009900">(</span>my.tempfile<span style="color: #339933">,</span>exdir=<a href="http://inside-r.org/r-doc/base/tempdir"><span style="color: #003399; font-weight: bold">tempdir</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #339933">,</span>junkpath=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#read space delimited text file extracted from zip</span><br />french_industry <span>&lt;-</span> <a href="http://inside-r.org/r-doc/utils/read.table"><span style="color: #003399; font-weight: bold">read.table</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a>=my.usefile<span style="color: #339933">,</span><br /> header = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> sep = <span style="color: #0000ff">""</span><span style="color: #339933">,</span><br /> as.is = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span><br /> skip = <span style="color: #cc66cc">11</span><span style="color: #339933">,</span> nrows=<span style="color: #cc66cc">1021</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get dates ready for xts index</span><br />datestoformat <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>french_industry<span style="color: #009900">)</span><br />datestoformat <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"01"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">"-"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get xts for analysis</span><br />french_industry_xts <span>&lt;-</span> as.xts<span style="color: #009900">(</span>french_industry<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">17</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> order.by=<a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>datestoformat<span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; french_industry_xts <span>&lt;-</span> french_industry_xts<span>/</span><span style="color: #cc66cc">100</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get price series from monthly returns for utilities and transports</span><br />Utils <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/cumprod"><span style="color: #003399; font-weight: bold">cumprod</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>+</span>french_industry_xts<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">14</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br />Trans <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/cumprod"><span style="color: #003399; font-weight: bold">cumprod</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>+</span>french_industry_xts<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">13</span><span style="color: #009900">]</span><span style="color: #009900">)</span> <span style="font-style: italic; color: #666666">#use chemicals #6 for best result</span><br />Utilsmean <span>&lt;-</span> runMean<span style="color: #009900">(</span>Utils<span style="color: #339933">,</span>n=<span style="color: #cc66cc">4</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get relative strength Utils to Transports</span><br />UtilsTrans <span>&lt;-</span> Utils<span>/</span>Trans&nbsp;&nbsp; width = <span style="color: #cc66cc">3</span><br /><span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>i <span style="color: #000000; font-weight: bold">in</span> <span style="color: #009900">(</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>Utils<span style="color: #009900">)</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> linmod <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/lm"><span style="color: #003399; font-weight: bold">lm</span></a><span style="color: #009900">(</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span><span style="color: #009900">(</span>i<span>-</span>width<span style="color: #009900">)</span><span>:</span>i<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span>~</span>index<span style="color: #009900">(</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span><span style="color: #009900">(</span>i<span>-</span>width<span style="color: #009900">)</span><span>:</span>i<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>i<span>==</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a> <span>&lt;-</span> coredata<span style="color: #009900">(</span>linmod<span>$</span>residuals<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>linmod<span>$</span>residuals<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a><span style="color: #339933">,</span>coredata<span style="color: #009900">(</span>linmod<span>$</span>residuals<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>linmod<span>$</span>residuals<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>i<span>==</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>signal2 <span>&lt;-</span> coredata<span style="color: #009900">(</span>linmod<span>$</span>coefficients<span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> signal2 <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span>signal2<span style="color: #339933">,</span>coredata<span style="color: #009900">(</span>linmod<span>$</span>coefficients<span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>i<span>==</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>signal3 <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/cor"><span style="color: #003399; font-weight: bold">cor</span></a><span style="color: #009900">(</span>linmod<span>$</span>fitted.values<span style="color: #339933">,</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span><span style="color: #009900">(</span>i<span>-</span>width<span style="color: #009900">)</span><span>:</span>i<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> signal3 <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span>signal3<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/cor"><span style="color: #003399; font-weight: bold">cor</span></a><span style="color: #009900">(</span>linmod<span>$</span>fitted.values<span style="color: #339933">,</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span><span style="color: #009900">(</span>i<span>-</span>width<span style="color: #009900">)</span><span>:</span>i<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="color: #009900">}</span>&nbsp;&nbsp; <a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a> <span>&lt;-</span> as.xts<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a><span style="color: #339933">,</span>order.by=index<span style="color: #009900">(</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>Utils<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />signal2 <span>&lt;-</span> as.xts<span style="color: #009900">(</span>signal2<span style="color: #339933">,</span>order.by=index<span style="color: #009900">(</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>Utils<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />signal3 <span>&lt;-</span> as.xts<span style="color: #009900">(</span>signal3<span style="color: #339933">,</span>order.by=index<span style="color: #009900">(</span>Utils<span style="color: #009900">[</span><span style="color: #009900">(</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>Utils<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />signal4 <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>Utils <span>&gt;</span> Utilsmean<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">0</span><span style="color: #009900">)</span>&nbsp;&nbsp; price_ret_signal <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>Utils<span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a><span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>signal2<span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>signal3<span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>signal4<span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>ROC<span style="color: #009900">(</span>Utils<span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">4</span><span style="color: #009900">)</span><span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> ROC<span style="color: #009900">(</span>Utils<span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span> <span>&lt;-</span> price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span>/</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><br />price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span> <span>&lt;-</span> price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span>/</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><br />ret <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span><span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span> <span>|</span> <span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">0</span> <span>&amp;</span><br /> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">12</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span> <span>&amp;</span> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">3</span><span style="color: #009900">)</span> <span>&lt;</span> <span style="color: #cc66cc">0</span> <span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <span style="color: #cc66cc">0</span><span style="color: #009900">)</span> <span>*</span> price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">]</span><br />retCompare <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>ret<span style="color: #339933">,</span> price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>retCompare<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Linear System"</span><span style="color: #339933">,</span> <span style="color: #0000ff">"BuyHoldUtils"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="performance summary.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6.25, height = 8, units="in",res=96)</span><br />charts.PerformanceSummary<span style="color: #009900">(</span>retCompare<span style="color: #339933">,</span>ylog=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span>cex.legend=<span style="color: #cc66cc">1.2</span><span style="color: #339933">,</span><br /> colorset=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"black"</span><span style="color: #339933">,</span><span style="color: #0000ff">"gray70"</span><span style="color: #009900">)</span><span style="color: #339933">,</span>main=<span style="color: #0000ff">"Utils System Return Comparison"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#eliminate NA at start of return series</span><br />retCompare<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/is.na"><span style="color: #003399; font-weight: bold">is.na</span></a><span style="color: #009900">(</span>retCompare<span style="color: #009900">)</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #cc66cc">0</span><br />price_system <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>Utils<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span><span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span> <span>|</span><br /> <span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">0</span> <span>&amp;</span> <br /> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">12</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span> <span>&amp;</span><br /> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">3</span><span style="color: #009900">)</span> <span>&lt;</span> <span style="color: #cc66cc">0</span> <span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <span style="color: #000000; font-weight: bold">NA</span><span style="color: #339933">,</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span>coredata<span style="color: #009900">(</span>Utils<span style="color: #009900">)</span><span style="color: #009900">[</span>width<span>+</span><span style="color: #cc66cc">12</span><span style="color: #009900">]</span><span>*</span><a href="http://inside-r.org/r-doc/base/cumprod"><span style="color: #003399; font-weight: bold">cumprod</span></a><span style="color: #009900">(</span>retCompare<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />price_system<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span> <span>&lt;-</span> price_system<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span>*</span>price_system<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>price_system<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"In"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Out"</span><span style="color: #339933">,</span><span style="color: #0000ff">"System"</span><span style="color: #009900">)</span>&nbsp;&nbsp; chartSeries<span style="color: #009900">(</span>price_system<span>$</span>System<span style="color: #339933">,</span>theme=<span style="color: #0000ff">"white"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/log"><span style="color: #003399; font-weight: bold">log</span></a>=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span>up.col=<span style="color: #0000ff">"black"</span><span style="color: #339933">,</span><br /> yrange=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/min"><span style="color: #003399; font-weight: bold">min</span></a><span style="color: #009900">(</span>price_system<span style="color: #009900">[</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/max"><span style="color: #003399; font-weight: bold">max</span></a><span style="color: #009900">(</span>price_system<span style="color: #009900">[</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> TA=<span style="color: #0000ff">"addTA(price_system$In,on=1,col=3);<br /> addTA(price_system$Out,on=1,col=2)"</span><span style="color: #339933">,</span><br /> name=<span style="color: #0000ff">"Utils Linear Model System"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#let's try an easy relative strength signal to choose small cap or large cap</span><br /><span style="font-style: italic; color: #666666">#know I can do this better in R but here is my ugly code</span><br /><span style="font-style: italic; color: #666666">#to calculate 12 month or 1 year slope of utils/trans</span><br />width=<span style="color: #cc66cc">12</span><br /><span style="font-style: italic; color: #666666">#get relative strength slope of high beta/low vol</span><br /><span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>i <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">1</span><span>:</span><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>UtilsTrans<span style="color: #009900">)</span><span>-</span>width<span style="color: #009900">)</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> model<span>&lt;-</span><a href="http://inside-r.org/r-doc/stats/lm"><span style="color: #003399; font-weight: bold">lm</span></a><span style="color: #009900">(</span>UtilsTrans<span style="color: #009900">[</span>i<span>:</span><span style="color: #009900">(</span>i<span>+</span>width<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span>~</span>index<span style="color: #009900">(</span>UtilsTrans<span style="color: #009900">[</span>i<span>:</span><span style="color: #009900">(</span>i<span>+</span>width<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>i<span>==</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>indexRS<span>&lt;-</span>model<span>$</span>coefficients<span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span>indexRS<span>&lt;-</span><a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span>indexRS<span style="color: #339933">,</span>model<span>$</span>coefficients<span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="color: #009900">}</span><br />indexRS<span>&lt;-</span><a href="http://inside-r.org/packages/cran/xts"><span>xts</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span>indexRS<span style="color: #009900">)</span><span style="color: #339933">,</span>order.by=index<span style="color: #009900">(</span>UtilsTrans<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #009900">(</span>width<span>+</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>UtilsTrans<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; price_ret_signal <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/na.omit"><span style="color: #003399; font-weight: bold">na.omit</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>price_ret_signal<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>indexRS<span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span> ROC<span style="color: #009900">(</span>Trans<span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#use same linear system signal for in out but add RS to choose Russell 2000 or SP500</span><br />retRS <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span><span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span> <span>|</span> <span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">]</span> <span>==</span> <span style="color: #cc66cc">0</span> <span>&amp;</span><br /> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">12</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span> <span>&amp;</span> runMean<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">3</span><span style="color: #009900">)</span> <span>&lt;</span> <span style="color: #cc66cc">0</span> <span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <span style="color: #cc66cc">0</span><span style="color: #009900">)</span> <span>*</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">8</span><span style="color: #009900">]</span><span>&lt;</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">9</span><span style="color: #009900">]</span><span style="color: #339933">,</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br />retCompareWithRS <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/na.omit"><span style="color: #003399; font-weight: bold">na.omit</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>retRS<span style="color: #339933">,</span>retCompare<span style="color: #339933">,</span>ROC<span style="color: #009900">(</span>Trans<span style="color: #339933">,</span> n=<span style="color: #cc66cc">1</span><span style="color: #339933">,</span> type=<span style="color: #0000ff">"discrete"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>retCompareWithRS<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Linear.With.RS"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>retCompareWithRS<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span>:</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"BuyHoldTrans"</span><span style="color: #009900">)</span>&nbsp;&nbsp; #<a href="http://inside-r.org/r-doc/grDevices/jpeg"><span style="color: #003399; font-weight: bold">jpeg</span></a><span style="color: #009900">(</span>filename=<span style="color: #0000ff">"performance summary.jpg"</span><span style="color: #339933">,</span><br /># quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">8</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br />charts.PerformanceSummary<span style="color: #009900">(</span>retCompareWithRS<span style="color: #339933">,</span>ylog=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span>cex.legend=<span style="color: #cc66cc">1.2</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Utility and Transports System Rotator"</span><span style="color: #339933">,</span> colorset=brewer.pal<span style="color: #009900">(</span><span style="color: #cc66cc">4</span><span style="color: #339933">,</span><span style="color: #0000ff">"Paired"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/mtext"><span style="color: #003399; font-weight: bold">mtext</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Source: http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html"</span><span style="color: #339933">,</span><br /> side=<span style="color: #cc66cc">1</span><span style="color: #339933">,</span>adj=<span style="color: #cc66cc">0</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">0.75</span><span style="color: #009900">)</span><br />#<a href="http://inside-r.org/r-doc/grDevices/dev.off"><span style="color: #003399; font-weight: bold">dev.off</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/boot/corr"><span style="color: #003399; font-weight: bold">corr</span></a> <span>&lt;-</span> runCor<span style="color: #009900">(</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #009900">]</span><span style="color: #339933">,</span>price_ret_signal<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">9</span><span style="color: #009900">]</span><span style="color: #339933">,</span>n=<span style="color: #cc66cc">12</span><span style="color: #009900">)</span><br />plot.zoo<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/boot/corr"><span style="color: #003399; font-weight: bold">corr</span></a><span style="color: #009900">)</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-5650599982312336719?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-6031438745093185922011-11-17T19:34:00.001-08:002011-11-17T19:40:48.889-08:00<p>I just wanted to quickly highlight the extremely fine work being done over at <a href="http://systematicinvestor.wordpress.com/">http://systematicinvestor.wordpress.com/</a>.&nbsp; The well documented statistical finance examples (mostly in R) are extremely helpful and stimulating.</p> <p>Some of my favorites are</p> <blockquote> <p><a href="http://systematicinvestor.wordpress.com/2011/11/16/black-litterman-model/">Black-Litterman Model</a></p> <p><a href="http://systematicinvestor.wordpress.com/2011/11/03/maximizing-omega-ratio/">Maximizing Omega Ratio</a></p> <p><a href="http://systematicinvestor.wordpress.com/2011/10/25/expected-shortfall-cvar-and-conditional-drawdown-at-risk-cdar-risk-measures/">Expected shortfall (CVaR) and Conditional Drawdown at Risk (CDaR)</a></p></blockquote> <p>Be sure to check it out.</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-603143874509318592?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-24901960816308738152011-11-16T09:11:00.001-08:002011-11-16T09:11:27.856-08:00<p>After reading Bloomberg’s article,</p> <blockquote> <p>JPMorgan Chase &amp; Co. and Goldman Sachs Group Inc., among the world’s biggest traders of credit derivatives, disclosed to shareholders that they have sold protection on more than $5 trillion of debt globally. <p><a href="http://bloom.bg/txiyuG">http://bloom.bg/txiyuG</a></p></blockquote> <p>I thought we should update my post <a href="http://timelyportfolio.blogspot.com/2011/07/scary-derivatives-and-scary-xml-in-r.html">Scary Derivatives and Scary XML in R</a> in which I said <blockquote> <p>The massive damage caused in 2008-2009 by the sliver of derivatives called credit default swaps seems like a faint warning siren when we see that they only represent &lt; 7% of total derivatives exposure. Interest rate and currency derivatives, also where I think the next disaster occurs, are more than 10 times larger than these credit contracts at $226 Trillion.</p></blockquote> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/GQZ6YXy6ST6W1JDtizxBGg?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-lV6OqQK0Ht4/TsPtoYd6vdI/AAAAAAACB3w/R6t9VSl4YEs/s800/derivatives%252520in%252520trillions.png" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>This amount of money, bilaterally netted or not, is truly unbelievable and staggering.&nbsp; Total debt outstanding of the sovereign nations is not the real problem.&nbsp; Like housing, the exponential exacerbation caused by the leverage and derivatives traded on the underlying is where the real potential catastrophe occurs.&nbsp; No government and no central bank has the ability to counter any major damage in currencies or interest rates.</p> <p>&nbsp;</p> <p><a href="https://docs.google.com/open?id=0B2qp2r96khJPYjUwNDNkNTktMGFkZC00ZGViLWEyNjAtNTZiZWI2M2VlMWNi">R code (click to download from Google Docs):</a></p> <p>#read xml derivatives data from the<br>#US Treasury OCC Quarterly Derivatives Report<br>#2 methods<br>#still way too manual since it appears the format changes<br>#each reporting period</p> <p>#as far as I can tell <br>#the first published example of how to read<br>#Microsoft Excel xml workbooks</p> <p>require(XML)<br>#require(ggplot2)</p> <p>#get 2nd Quarter of 2011 report (dq211)<br>url = "<a href="http://www.occ.treas.gov/topics/capital-markets/financial-markets/trading/derivatives/dq211-xml.xml&quot;">http://www.occ.treas.gov/topics/capital-markets/financial-markets/trading/derivatives/dq211-xml.xml"</a></p> <p>doc = xmlInternalTreeParse(url)<br>#define namespaces<br>#figuring this out took hours<br>#but using getNodeSet was much cleaner than the<br>#next method<br>namespaces = c(o="urn:schemas-microsoft-com:office:office",<br>&nbsp;&nbsp;&nbsp; x="urn:schemas-microsoft-com:office:excel",<br>&nbsp;&nbsp;&nbsp; ss="urn:schemas-microsoft-com:office:spreadsheet",<br>&nbsp;&nbsp;&nbsp; html="<a href="http://www.w3.org/TR/REC-html40&quot;)">http://www.w3.org/TR/REC-html40")</a><br>#this gets row 41 from the Table 3 worksheet for the total $ of derivatives<br>ns &lt;- getNodeSet(doc,"/ss:Workbook/ss:Worksheet[@ss:Name='Table 3']/ss:Table/ss:Row",namespaces)[[41]]<br>amt &lt;- df &lt;- as.data.frame(as.numeric(xmlSApply(ns, xmlValue))[4:11])<br>#believe it or not this is $trillions of dollars<br>#remove some zeros so we can label better on the graph<br>amt &lt;- amt/1000000<br>df &lt;- df/1000000<br>#this gets row 10 for labels<br>ns &lt;- getNodeSet(doc,"/ss:Workbook/ss:Worksheet[@ss:Name='Table 3']/ss:Table/ss:Row",namespaces)[[10]]<br>lab &lt;- as.character(xmlSApply(ns, xmlValue)[4:11])<br>#combine the labels with <br>df &lt;- cbind(lab,df)<br>#jpeg(filename="derivatives by type.jpg",quality=100,<br>#&nbsp;&nbsp;&nbsp; width=6.25, height = 8,&nbsp; units="in",res=96)<br>barplot(df[5:8,2],names.arg = factor(df[5:8,1]),main="US Bank Derivatives by Type<br>&nbsp;&nbsp;&nbsp; Q2 2011",ylab="$ (in trillions)",ylim=c(0,max(df[5:8,2]+50)),space=0,<br>&nbsp;&nbsp;&nbsp; col=c("indianred4","darkolivegreen4","cadetblue4","goldenrod3"))<br>mtext("Source: US Dept of Treasury OCC Quarterly Derivatives Report",<br>&nbsp;&nbsp;&nbsp; side=1,line=3,cex=0.8,adj=0)<br>#dev.off()</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2490196081630873815?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-66955875740166202682011-11-01T10:19:00.001-07:002011-11-01T12:30:07.780-07:00<p>When we learn the efficient frontier, most are misled to believe that the frontier is static and unchanging.&nbsp; However, we should have all learned by recent experience that the frontier is as volatile as the assets that construct it.&nbsp; If we look at just US Stocks (SP 500) and US Bonds (Barclays Agg), we can see how this shifting frontier can dramatically affect your returns.</p> <p>Using R and fPortfolio, let’s construct the frontier every rolling 5-year period to see what has happened since 1975.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/5ALIOO5hmDo2Yq7fnUKe5A?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-CM6bqzodBPk/TrBIZfab6-I/AAAAAAAB-HA/ZyxidHfBRKA/s800/evolving%252520frontier.jpg" width="576" height="720"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/open?id=0B2qp2r96khJPNjY5MWJmMTYtODIzYi00YzNmLTg2ZjQtNjk0MGMzNTllNzI3">R code (click to download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/fPortfolio"><span>fPortfolio</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/stats/reshape"><span style="color: #003399; font-weight: bold">reshape</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#############################################################</span><br /><span style="font-style: italic; color: #666666">#get data; unfortunately cannot share since I would violate</span><br /><span style="font-style: italic; color: #666666">#copyright</span><br />sp_agg <span>&lt;-</span> <a href="http://inside-r.org/r-doc/utils/read.csv"><span style="color: #003399; font-weight: bold">read.csv</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"C:<span style="color: #000099; font-weight: bold">\\</span>Users<span style="color: #000099; font-weight: bold">\\</span>Kent.TLEAVELL_NT<span style="color: #000099; font-weight: bold">\\</span>Documents<span style="color: #000099; font-weight: bold">\\</span>old<span style="color: #000099; font-weight: bold">\\</span>R<span style="color: #000099; font-weight: bold">\\</span>sp_agg.csv"</span><span style="color: #339933">,</span>stringsAsFactors=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">)</span><br />sp_agg <span>&lt;-</span> sp_agg<span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">)</span><span style="color: #009900">]</span><br />sp_agg <span>&lt;-</span> sp_agg<span style="color: #009900">[</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #009900">)</span><span style="color: #009900">]</span>&nbsp;&nbsp; len <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/nchar"><span style="color: #003399; font-weight: bold">nchar</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br />xtsdate <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>len<span>-</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span>len<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"-"</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>len<span>==</span><span style="color: #cc66cc">9</span><span style="color: #339933">,</span><span style="color: #0000ff">"0"</span><span style="color: #339933">,</span><span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/substr"><span style="color: #003399; font-weight: bold">substr</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>len<span>-</span><span style="color: #cc66cc">8</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"-01"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span>&nbsp;&nbsp; sp_agg.xts <span>&lt;-</span> <a href="http://inside-r.org/packages/cran/xts"><span>xts</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/data.matrix"><span style="color: #003399; font-weight: bold">data.matrix</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>sp_agg<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span>order.by=<a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>xtsdate<span style="color: #009900">)</span><span style="color: #009900">)</span><br />sp_agg.xts <span>&lt;-</span> sp_agg.xts<span>/</span><span style="color: #cc66cc">100</span><br /><span style="font-style: italic; color: #666666">#############################################################</span>&nbsp;&nbsp;&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#for svg</span><br /><span style="font-style: italic; color: #666666">#require(Cairo)</span><br /><span style="font-style: italic; color: #666666">#CairoSVG("frontier.svg", width=8 ,height=8 )</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="evolving frontier.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6, height = 7.5, units="in",res=96)#############################################################</span><br /><span style="font-style: italic; color: #666666">## spec -</span><br /> Spec = portfolioSpec<span style="color: #009900">(</span><span style="color: #009900">)</span><br /> setTargetReturn<span style="color: #009900">(</span>Spec<span style="color: #009900">)</span> = <a href="http://inside-r.org/r-doc/base/mean"><span style="color: #003399; font-weight: bold">mean</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/colMeans"><span style="color: #003399; font-weight: bold">colMeans</span></a><span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">## constraints -</span><br /> Constraints = <span style="color: #0000ff">"LongOnly"</span><br /><span style="font-style: italic; color: #666666">#get frontiers by 5-year range</span><br />from = <a href="http://inside-r.org/r-doc/stats/time"><span style="color: #003399; font-weight: bold">time</span></a><span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">49</span><span style="color: #339933">,</span><span style="color: #cc66cc">109</span><span style="color: #339933">,</span><span style="color: #cc66cc">169</span><span style="color: #339933">,</span><span style="color: #cc66cc">229</span><span style="color: #339933">,</span><span style="color: #cc66cc">289</span><span style="color: #339933">,</span><span style="color: #cc66cc">349</span><span style="color: #339933">,</span><span style="color: #cc66cc">385</span><span style="color: #009900">)</span><span style="color: #009900">]</span><br />to = <a href="http://inside-r.org/r-doc/stats/time"><span style="color: #003399; font-weight: bold">time</span></a><span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">48</span><span style="color: #339933">,</span><span style="color: #cc66cc">108</span><span style="color: #339933">,</span><span style="color: #cc66cc">168</span><span style="color: #339933">,</span><span style="color: #cc66cc">228</span><span style="color: #339933">,</span><span style="color: #cc66cc">288</span><span style="color: #339933">,</span><span style="color: #cc66cc">348</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">8</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">8</span><span style="color: #009900">)</span><span style="color: #009900">]</span>&nbsp;&nbsp; rollFron <span>&lt;-</span> rollingPortfolioFrontier<span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>sp_agg.xts<span style="color: #009900">)</span><span style="color: #339933">,</span>Spec<span style="color: #339933">,</span>Constraints<span style="color: #339933">,</span><br /> from=from<span style="color: #339933">,</span>to=to<span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#chartcol &lt;- topo.colors(length(rollFron))</span><br />chartcol <span>&lt;-</span> <span style="color: #cc66cc">1</span><span>:</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>rollFron<span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#hindsight bias; yellow is too hard to read so change</span><br />chartcol<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>rollFron<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #0000ff">"goldenrod"</span>&nbsp;&nbsp;&nbsp;&nbsp; i=<span style="color: #cc66cc">1</span><br />frontierPlot<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>chartcol<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>xlim=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">0.08</span><span style="color: #009900">)</span><span style="color: #339933">,</span>ylim=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span>-</span><span style="color: #cc66cc">0.01</span><span style="color: #339933">,</span><span style="color: #cc66cc">0.025</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />frontierlabels <span>&lt;-</span> frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span>x=frontierlabels<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>frontierlabels<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>y=frontierlabels<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>frontierlabels<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/labels"><span style="color: #003399; font-weight: bold">labels</span></a>=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span>from<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">" to "</span><span style="color: #339933">,</span>to<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> pos=<span style="color: #cc66cc">4</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/offset"><span style="color: #003399; font-weight: bold">offset</span></a>=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>i <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">2</span><span>:</span><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>rollFron<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">3</span><span style="color: #009900">)</span> <span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> frontierPlot<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #339933">,</span>add=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = <a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span>auto=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/graphics/title"><span style="color: #003399; font-weight: bold">title</span></a>=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">)</span><br /> frontierlabels <span>&lt;-</span> frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span>x=frontierlabels<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>frontierlabels<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>y=frontierlabels<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>frontierlabels<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/labels"><span style="color: #003399; font-weight: bold">labels</span></a>=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span>from<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">" to "</span><span style="color: #339933">,</span>to<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> pos=<span style="color: #cc66cc">4</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/offset"><span style="color: #003399; font-weight: bold">offset</span></a>=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><br /><span style="color: #009900">}</span>&nbsp;&nbsp; i=<span style="color: #cc66cc">7</span><br />lowerFrontier = frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a> = <span style="color: #0000ff">"both"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>lowerFrontier<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = <a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #009900">)</span><br />frontierlabels <span>&lt;-</span> frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span>x=frontierlabels<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>y=frontierlabels<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/labels"><span style="color: #003399; font-weight: bold">labels</span></a>=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span>from<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">" to "</span><span style="color: #339933">,</span>to<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> pos=<span style="color: #cc66cc">4</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/offset"><span style="color: #003399; font-weight: bold">offset</span></a>=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp;&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#legend("topright",legend=paste(from,to,sep=" "),pch=19,</span><br /><span style="font-style: italic; color: #666666"># col=chartcol,cex=0.7)</span><br /><span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>i <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">8</span><span>:</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>rollFron<span style="color: #009900">)</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> lowerFrontier = frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a> = <span style="color: #0000ff">"lower"</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>lowerFrontier<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = <a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #009900">)</span><br /> frontierlabels <span>&lt;-</span> frontierPoints<span style="color: #009900">(</span>rollFron<span style="color: #009900">[</span><span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a>=<span style="color: #0000ff">"lower"</span><span style="color: #009900">)</span><br /> <a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span>x=frontierlabels<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span>y=frontierlabels<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/labels"><span style="color: #003399; font-weight: bold">labels</span></a>=<a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span>from<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">" to "</span><span style="color: #339933">,</span>to<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> pos=<span style="color: #cc66cc">4</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/offset"><span style="color: #003399; font-weight: bold">offset</span></a>=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">0.5</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = chartcol<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><br /><span style="color: #009900">}</span><br /><span style="font-style: italic; color: #666666">#</span><br /><span style="font-style: italic; color: #666666">#frontier &lt;- portfolioFrontier(as.timeSeries(sp_agg.xts))</span><br /><span style="font-style: italic; color: #666666">#frontierPlot(frontier,col=rep(chartcol[length(rollFron)+1],2),add=TRUE,pch=19,auto=FALSE,</span><br /><span style="font-style: italic; color: #666666"># title=FALSE)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-6695587574016620268?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-59250908039290002002011-10-20T14:28:00.001-07:002011-10-20T14:31:17.761-07:00<span xmlns=""></span><br /><span xmlns="">My family is off to DisneyWorld for a week, so there will not be any posts while I am there. However, I thought it would be interesting to see how Disney stock has done since my last trip September 2010.<br />Maybe since Disney has done so poorly, the crowds will be smaller. Of course I know better than that.<br />Maybe since the Japanese Yen has continued to do so well, there will be more Japanese at the parks.<br />It is interesting how well XLY (Consumer Discretionary) over the last 1 year. I guess US consumers really are special.<br /><table style="width:auto;"><tr><td><a href="https://picasaweb.google.com/lh/photo/0G206VgBhAD46Cxt6PmejA?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-hLoVHpmKriI/TqCRtIp6D5I/AAAAAAAB498/TuUhNJmZflE/s800/performance%252520summary.jpeg" height="665" width="666" /></a></td></tr><tr><td style="font-family:arial,sans-serif; font-size:11px; text-align:right">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&feat=embedwebsite">TimelyPortfolio</a></td></tr></table>R code:<br />require(quantmod)<br />require(PerformanceAnalytics)<br /><br /><br />tckrs &lt;- c("spy","xly","dis","eem","fxy")<br /><br /><br />getSymbols(tckrs,from="2010-09-15",to=Sys.Date(),adjust=TRUE)<br /><br /><br />stocks &lt;- merge(DIS[,4],SPY[,4],XLY[,4],EEM[,4],FXY[,4])<br />colnames(stocks) &lt;- c("DIS","SPY","XLY","EEM","FXY")<br />stocks.roc &lt;- ROC(stocks,n=1,type="discrete")<br />stocks.roc[1,] &lt;- 0<br /><br /><br />charts.PerformanceSummary(stocks.roc,lwd=2,<br />&nbsp;&nbsp;&nbsp;&nbsp;colorset=c("indianred3","steelblue4","darkolivegreen3","gray70","purple"),<br />&nbsp;&nbsp;&nbsp;&nbsp;main="Since My Last Trip to Disney",cex.legend=1.2)</span><div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-5925090803929000200?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-87438063032565504392011-10-13T12:52:00.001-07:002011-10-13T12:52:10.940-07:00<p>On Twitter last night, I spotted @milktrader from <a href="http://www.algorithmzoo.com">www.algorithmzoo.com</a> doing some range research on equity indexes.&nbsp; I offered a tweet on the crazy Russell 2000 17% move over 7 days.&nbsp; Within 10 minutes, I discovered a signal that worked very well.&nbsp; It probably is worthless, but I thought I would share in case someone cares to play with it.&nbsp; THIS IS NOT INVESTMENT ADVICE AND WILL PROBABLY LOSE INCREDIBLE AMOUNTS OF MONEY.&nbsp; If nothing else, it illustrates the power of R.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/8VkGW2nFQQimvIDPrczHJw?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-etsKysjI9kg/TpdBAoui_rI/AAAAAAAB3t0/iA1IxikOo5U/s800/twitter%252520russell%2525202000.png" width="553" height="552"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/x2LXRMoOeH0S6Mjh0Ksfrg?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-y0MkvA3zU-Q/TpdBAt7TH-I/AAAAAAAB3tw/_PYaxbHfgOI/s800/twitter%252520kospi.png" width="553" height="552"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>R code:</p> <p>require(quantmod)<br>require(PerformanceAnalytics)<br>getSymbols("^RUT",from="1896-01-01",to=Sys.Date())<br>signal&lt;-ifelse(runMax(RUT[,2],7)/runMin(RUT[,3],7)-1-<br>&nbsp;&nbsp;&nbsp; ROC(RUT[,4],n=20,type="discrete")&lt;0.02,1,0)<br>perf&lt;-merge(lag(signal,k=1)*ROC(RUT[,4],type="discrete",n=1),<br>&nbsp;&nbsp;&nbsp; ROC(RUT[,4],type="discrete",n=1))<br>colnames(perf)&lt;-c("System","Russell 2000")<br>charts.PerformanceSummary(perf,ylog=TRUE,<br>&nbsp;&nbsp;&nbsp; main="Quick Untested Russell 2000 System")</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8743806303256550439?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-81202518068236866382011-10-12T08:45:00.001-07:002011-10-12T08:45:13.217-07:00<p>The only thing that separates the United States from Europe and the notorious PIIGS is the generosity of Asian Central Banks who have been consistently quantitatively easing since 1998 (<a href="http://timelyportfolio.blogspot.com/2011/07/join-reserves.html">Join the Reserves</a>).</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/COD1GQ45hzS3P3Bkz7TFeA?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-sbP4rIQXh6g/TjDNwXkKckI/AAAAAAABy90/TwqmILAKeuU/s800/oecd%252520cofer%252520reserves%252520area%252520chart.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Without this generosity, the United States could very easily have entered a death spiral (see <a href="http://timelyportfolio.blogspot.com/2011/03/death-spiral-of-country.html">Death Spiral of a Country</a> and <a href="http://timelyportfolio.blogspot.com/2011/03/death-spiral-warning-graph.html">Death Spiral Warning Graph</a>) in 2008 and still might fall into this disastrous trap.</p> <p>Deliberately attacking this very tenuous thread seems foolish, but this foolish action has found support with our fine politicians <a href="http://www.washingtonpost.com/blogs/2chambers/post/senate-approves-china-currency-bill/2011/10/11/gIQAhvaUdL_blog.html">Washington Post "Senate approves China currency bill"</a>.&nbsp; The US needs to recruit some US $ buyers, but unfortunately there are none to fill the multi-trillion dollar gap.</p> <p>Even more concerning is the focus on China who has been steadily attacking the problem.&nbsp; The focus on China does not make sense when you look at the appreciation of the Chinese Yuan.&nbsp; I see a lot more Korean cars on the road and TVs and appliances in the stores, but I do not hear any mention of the extreme undervaluation of the Korean Won to the US$ but especially the Japanese Yen, so it appears the Koreans Won.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/vOyeuG_7k8IhiaodKzDMYg?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-fC0jGa_ppF4/TpW1sVuhxAI/AAAAAAAB1lE/16qi3eA6Ajw/s800/yuan%252520won.jpeg" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>I agree that the US$ reserve building needs to stop, but let’s not deliberately induce a positive feedback death spiral.</p> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMDVjMWE3ZjktMTM0Yi00MzkyLWI0MmQtOWM5MTBjNzRmYzBh&amp;hl=en_US">R code (click to download from Google Docs):</a></p> <p>require(quantmod)<br>require(PerformanceAnalytics)</p> <p>getSymbols("DEXCHUS",src="FRED")<br>getSymbols("DEXKOUS",src="FRED")</p> <p>plot.zoo(merge(1/DEXCHUS,100/DEXKOUS)["1997::",],screens=1,lwd=2,<br>&nbsp;&nbsp;&nbsp; col=c("lightblue4","antiquewhite4"),<br>&nbsp;&nbsp;&nbsp; xlab="Year",ylab=NA,<br>&nbsp;&nbsp;&nbsp; main="Chinese Yuan and Korean Won<br>&nbsp;&nbsp;&nbsp; 1997 to Sep 2011")<br>legend("right", c("China","Korea"), lwd = 2, bty="n",<br>&nbsp;&nbsp;&nbsp; col=c("lightblue4","antiquewhite4"),y.intersp=2,<br>&nbsp;&nbsp;&nbsp; text.col=c("lightblue4","antiquewhite4"))</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8120251806823686638?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-89786512298074376452011-10-07T09:32:00.001-07:002011-10-07T09:32:30.885-07:00<p>Hopefully you have been able to persist with me through</p> <blockquote> <p><a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-this-is-test-test-3data-snoopy.html">ttrTests This is a Test Test 3:Data Snoopy</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-this-is-test-test-1-and-test-2.html">ttrTests This is a Test--Test 1 and Test 2</a></p> <p><a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-its-great-thesis-and.html">ttrTests: Its Great Thesis and Incredible Potentia...</a></p></blockquote> <p>For the 4th and final ttrTest, we will check for the persistence of parameters across subperiods and then across subperiods with bootstrapped samples for each subperiod.&nbsp; Not surprisingly, CUD failed most of the tests.&nbsp; However, reader <a href="http://www.blogger.com/profile/17531709989988993379">iQuant</a> is one step ahead of me in his comment:</p> <dl> <dd> <p>“Nice research piece, thank you! I was wondering whether we should consider the interest earned in cash positions as well the cost of going short. In long term strategies such as the one presented by Professor St. John this may make a lot of difference, favouring low frequency parameter sets and increasing the conditional excess returns of zero-weigth positions. </p> <dd><a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-this-is-test-test-3data-snoopy.html?showComment=1317584803821#c1363450789246798346">October 2, 2011 12:46 PM </a>“</dd></dl> <p>I will attempt to address this very valid concern in future posts.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/yG474fryqVoMHzTHvML1fw?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-SB1SdlBqOSA/To8mDzC98CI/AAAAAAAB1QY/4wVuGfKM7uI/s800/boxplot.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/88t_ijjelUXTMU_skgSwbQ?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-GEEbojHJi9Q/To8mEEG2_XI/AAAAAAAB1Qc/tE2K89GzjZg/s800/strip%252520chart.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>For the most intense test, we will bootstrap multiple samples across multiple subperiods. The prettiness of the graph unfortunately does not indicate the power of the test.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/UUG_kGfSvUAVWlLL0l1AbA?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-9CUiqsew-bA/To8mD5PTkgI/AAAAAAAB1QU/6jAv0jFml5k/s800/paramPersist%252520correlations.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPZDE3YjI2YTQtMTcxNS00N2M2LTlmNjktNWVjY2M0ZTY2NDc3&amp;hl=en_US">R code (click to download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><span style="font-style: italic; color: #666666">#let's define our silly countupdown function</span><br /><span style="font-style: italic; color: #666666">#as a sample of a custom ttr rule</span><br />CUD <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/function"><span style="color: #003399; font-weight: bold">function</span></a><span style="color: #009900">(</span>x<span style="color: #339933">,</span>params=<span style="color: #cc66cc">50</span><span style="color: #339933">,</span>...<span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <span style="font-style: italic; color: #666666">#CUD takes the n-period sum of 1 (up days) and -1 (down days)</span><br /> temp <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>runSum<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>ROC<span style="color: #009900">(</span>x<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span>-</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span>params<span style="color: #009900">)</span><span>&gt;=</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">0</span><span style="color: #009900">)</span><br /> <span style="font-style: italic; color: #666666">#replace NA with 0 at beginning of period</span><br /> temp<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/is.na"><span style="color: #003399; font-weight: bold">is.na</span></a><span style="color: #009900">(</span>temp<span style="color: #009900">)</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #cc66cc">0</span><br /> temp<br /><span style="color: #009900">}</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/ttrTests"><span>ttrTests</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/lattice"><span>lattice</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span>reshape2<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#defaults functions is overridden by ggplot2 and plyr if loaded</span><br /><span style="font-style: italic; color: #666666">#and will cause problems if you want to use ttrTests concurrently</span>&nbsp;&nbsp; tckrs <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"GSPC"</span><span style="color: #339933">,</span><span style="color: #0000ff">"RUT"</span><span style="color: #339933">,</span><span style="color: #0000ff">"N225"</span><span style="color: #339933">,</span><span style="color: #0000ff">"GDAXI"</span><span style="color: #339933">,</span><span style="color: #0000ff">"DJUBS"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#use 1 or GSPC but adjust however you would like</span><br />i=<span style="color: #cc66cc">1</span><br />getSymbols<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"^"</span><span style="color: #339933">,</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span>to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />test_price <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.vector"><span style="color: #003399; font-weight: bold">as.vector</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/get"><span style="color: #003399; font-weight: bold">get</span></a><span style="color: #009900">(</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#run subperiods and paramPersist to test for luck across subperiods</span><br /><span style="font-style: italic; color: #666666">#"asks whether or not good choices of parameters"</span><br /><span style="font-style: italic; color: #666666">#"were robust across different time periods"</span><br /><span style="font-style: italic; color: #666666">#chose 6 since data is from 1950 will approximate by decade</span><br />subper <span>&lt;-</span> subperiods<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> periods = <span style="color: #cc66cc">6</span><span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a> = CUD<span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/start"><span style="color: #003399; font-weight: bold">start</span></a> = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> nSteps = <span style="color: #cc66cc">30</span><span style="color: #339933">,</span> stepSize = <span style="color: #cc66cc">10</span><span style="color: #339933">,</span> restrict = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span><br /> burn = <span style="color: #cc66cc">0</span><span style="color: #339933">,</span> short = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> condition = <span style="color: #000000; font-weight: bold">NULL</span><span style="color: #339933">,</span><br /> silent = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> TC = <span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> loud = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> alpha = <span style="color: #cc66cc">0.025</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a> = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> benchmark = <span style="color: #0000ff">"hold"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span> <span>&lt;-</span> <span style="color: #0000ff">"obs.correlation"</span><br /><span style="font-style: italic; color: #666666">#while we are in a nasty for loop; grab some data also</span><br /><span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>j <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">3</span><span>:</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">)</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"excess.return"</span><span style="color: #339933">,</span><span style="color: #0000ff">"z.score"</span><span style="color: #339933">,</span><span style="color: #0000ff">"adj.excess.return"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"Sharpe.ratio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best.repeat"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best.adjusted"</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"tested.parameters"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">7</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <span style="font-style: italic; color: #666666"># add this if desired ".subper",j-2, sep="")</span><br /> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>j<span>==</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span> excess.df <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>j<span>-</span><span style="color: #cc66cc">2</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>tested.parameters<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>tested.parameters<span style="color: #339933">,</span><br /> subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>excess.return<span style="color: #009900">)</span><span style="color: #339933">,</span><br /> excess.df <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span>excess.df<span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/rep"><span style="color: #003399; font-weight: bold">rep</span></a><span style="color: #009900">(</span>j<span>-</span><span style="color: #cc66cc">2</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/length"><span style="color: #003399; font-weight: bold">length</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>tested.parameters<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>tested.parameters<span style="color: #339933">,</span><br /> subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>excess.return<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="color: #009900">}</span><br />excess.df <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.data.frame"><span style="color: #003399; font-weight: bold">as.data.frame</span></a><span style="color: #009900">(</span>excess.df<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>excess.df<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"subperiod"</span><span style="color: #339933">,</span><span style="color: #0000ff">"parameter"</span><span style="color: #339933">,</span><span style="color: #0000ff">"excess.ret"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#run boxplot of excess returns by parameter</span><br /><a href="http://inside-r.org/r-doc/grDevices/jpeg"><span style="color: #003399; font-weight: bold">jpeg</span></a><span style="color: #009900">(</span>filename=<span style="color: #0000ff">"boxplot.jpg"</span><span style="color: #339933">,</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/boxplot"><span style="color: #003399; font-weight: bold">boxplot</span></a><span style="color: #009900">(</span>excess.df<span>$</span>excess.ret<span>~</span>excess.df<span>$</span>parameter<span style="color: #339933">,</span> <br /> xlab=<span style="color: #0000ff">"Parameter"</span><span style="color: #339933">,</span> ylab=<span style="color: #0000ff">"Excess Return"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Boxplot of Excess Returns by Parameter"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/grDevices/dev.off"><span style="color: #003399; font-weight: bold">dev.off</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="strip chart.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6.25, height = 6.25, units="in",res=96)</span><br /><a href="http://inside-r.org/r-doc/graphics/stripchart"><span style="color: #003399; font-weight: bold">stripchart</span></a><span style="color: #009900">(</span>excess.df<span>$</span>excess.ret<span>~</span>excess.df<span>$</span>parameter<span style="color: #339933">,</span> pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span><br /> xlab=<span style="color: #0000ff">"Parameter"</span><span style="color: #339933">,</span> ylab=<span style="color: #0000ff">"Excess Return"</span><span style="color: #339933">,</span> vertical=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/grDevices/topo.colors"><span style="color: #003399; font-weight: bold">topo.colors</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>subper<span style="color: #009900">[</span><span style="color: #009900">[</span>j<span style="color: #009900">]</span><span style="color: #009900">]</span><span>$</span>tested.parameters<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Stripchart of Excess Returns by Parameter"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp;&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#and my favorite of all</span><br /><span style="font-style: italic; color: #666666">#"tests if the persistence measure from subperiods()"</span><br /><span style="font-style: italic; color: #666666">#"is statistically significant"</span><br /><span style="font-style: italic; color: #666666">#this takes the longest (about 28 minutes on my i7 laptop)</span><br /><span style="font-style: italic; color: #666666">#if you want to play </span><br /><span style="font-style: italic; color: #666666">#change periods to 2 or bsamples to 10 to speed time</span><br />parpersist <span>&lt;-</span> paramPersist<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a> = CUD<span style="color: #339933">,</span> periods=<span style="color: #cc66cc">6</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats/start"><span style="color: #003399; font-weight: bold">start</span></a> = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> nSteps = <span style="color: #cc66cc">30</span><span style="color: #339933">,</span> stepSize = <span style="color: #cc66cc">10</span><span style="color: #339933">,</span><br /> bSamples=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span><br /> restrict = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> burn = <span style="color: #cc66cc">0</span><span style="color: #339933">,</span> short = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> condition = <span style="color: #000000; font-weight: bold">NULL</span><span style="color: #339933">,</span><br /> silent = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> TC = <span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> loud = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> alpha = <span style="color: #cc66cc">0.025</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a> = <span style="color: #0000ff">""</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>parpersist<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"act.corr"</span><span style="color: #339933">,</span><span style="color: #0000ff">"obs.corr.samples"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p.value"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="paramPersist correlations.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6.25, height = 6.25, units="in",res=96)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>parpersist<span>$</span>obs.corr.samples<span style="color: #339933">,</span>ylab=<span style="color: #0000ff">"Correlation"</span><span style="color: #339933">,</span>xlab=<span style="color: #0000ff">"Sample"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"paramPersist for CUD"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>h=parpersist<span>$</span>act.corr<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"darkslateblue"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/text"><span style="color: #003399; font-weight: bold">text</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span>parpersist<span>$</span>act.corr<span style="color: #339933">,</span> <span style="color: #0000ff">"actual"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a> = <span style="color: #0000ff">"darkslateblue"</span><span style="color: #339933">,</span> adj = <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span> <span>-</span><span style="color: #cc66cc">.1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>snoop<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"details"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V2"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"V3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p1.for.l"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p2.for.c"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p3.for.u"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="dataSnoop values.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>snoop<span>$</span>V3<span style="color: #339933">,</span><br /> type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">2</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"ttrTests dataSnoop V1,V2,and V3 on CUD"</span><span style="color: #339933">,</span><br /> xlab=<span style="color: #0000ff">"Bootstrap Sample"</span><span style="color: #339933">,</span> ylab=<span style="color: #0000ff">"Values"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>snoop<span>$</span>V2<span style="color: #339933">,</span> type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">3</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>snoop<span>$</span>V1<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">4</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"topright"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"V1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V2"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V3"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">4</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span>lty=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8978651229807437645?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com1tag:blogger.com,1999:blog-7630810606654250077.post-44302378010731186372011-10-06T13:28:00.001-07:002011-10-06T14:33:52.560-07:00<p>In my mind, there are two very disparate views in the money management space: Markowitz style diversification and Faber style tactical allocation.</p><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=1118008855&amp;nou=1&amp;ref=tf_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe><iframe style="width: 120px; height: 240px" marginheight="0" src="http://rcm.amazon.com/e/cm?t=timelyp-20&amp;o=1&amp;p=8&amp;l=as1&amp;asins=1557861080&amp;nou=1&amp;ref=tf_til&amp;fc1=000000&amp;IS2=1&amp;lt1=_blank&amp;m=amazon&amp;lc1=0000FF&amp;bc1=000000&amp;bg1=FFFFFF&amp;f=ifr" frameborder="0" marginwidth="0" scrolling="no"></iframe> <p>I thought it would be fun to see what happens when we try to blend the two with an efficient frontier between two assets—”buy and hold” S&amp;P 500 and a Faber 10-month tactical S&amp;P 500 strategy.&nbsp; In the process I will also introduce the <a href="http://www.rmetrics.org/files/freepdf/PortfolioOptimizationSample.pdf">fPortfolio package</a>.</p> <p>If we take the 10 month moving average S&amp;P 500 system</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/OqLumZxnSj-VfW4u2RpcSw?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-U_On3MCOEf0/To23zfGz9KI/AAAAAAAB1QE/WvWY60SEMB4/s800/performance%252520summary.jpg" width="576" height="720"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>and treat it as a separate asset class, the efficient frontier since 1950 would look like this.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/zOaXFJs-DR4FIiS1S1-1hA?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/--zrYl1gSRvA/To23zICgqKI/AAAAAAAB1P4/6zXXZcmpPOk/s800/frontier%252520plot.jpg" width="576" height="576"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>I think this is an interesting and unique way to look at it.&nbsp; If we then take the rolling tangency portfolio the allocation would fluctuate and fairly closely mark bear and bull equity markets.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/Xq0ECKhVmxdbK-qJ4L-XVA?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-yqXBimgjLCI/To23z4YpOAI/AAAAAAAB1QI/PEgsbw3c5wY/s800/rollling%252520weight%252520plot.jpg" width="576" height="576"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>AS ALWAYS THIS IS NOT INVESTMENT ADVICE, JUST A FUN EXPERIMENT. SIGNIFICANT LOSSES ARE HIGHLY LIKELY IF YOU PURSUE THIS APPROACH.</p> <p>The blended allocation looks fairly good.&nbsp; There was no optimization or backtesting.&nbsp; Please let me know if you discover improvements.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/ND94NkgZJ7jp5t_El0J7Mw?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-oF4c8mU0X54/To23zqz99kI/AAAAAAAB1QA/ReliWm7x2-s/s800/risk%252520return.jpg" width="576" height="576"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/h0n4OcIADLzRydVVRjUTtw?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-oGRCeXDokI8/To23zbYdonI/AAAAAAAB1P8/XdXEMWct5xY/s800/perf%252520all.jpg" width="576" height="672"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPNzE3MTViMDgtMGFjOS00NjM2LTlkNWYtYTQ1NzY5OGFlMTNh&amp;hl=en_US">R code (download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get GSPC or S&amp;P 500</span><br /><span style="font-style: italic; color: #666666">#feel free to change to whatever you would like</span><br /><span style="font-style: italic; color: #666666">#for non index do not include ^</span><br />getSymbols<span style="color: #009900">(</span><span style="color: #0000ff">"^GSPC"</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span>to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get monthly close</span><br />sp500 <span>&lt;-</span> to.monthly<span style="color: #009900">(</span>GSPC<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><br /><span style="font-style: italic; color: #666666">#do this to get from mmm yyyy to yyyy-mm-dd</span><br />index<span style="color: #009900">(</span>sp500<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>index<span style="color: #009900">(</span>sp500<span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#get monthly returns from the monthly closes</span><br /><span style="font-style: italic; color: #666666">#multiple ways of doing this</span><br />sp500.ret <span>&lt;-</span> monthlyReturn<span style="color: #009900">(</span>sp500<span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get 10 month Mebane Faber moving average</span><br />ma <span>&lt;-</span> runMean<span style="color: #009900">(</span>sp500<span style="color: #339933">,</span>n=<span style="color: #cc66cc">10</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#if close &gt; 10 month moving average then 1 and 0 if &lt;</span><br /><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>sp500 <span>&gt;</span> ma<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">0</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#merge originial return data with this new data</span><br /><span style="font-style: italic; color: #666666">#multiply the 1-month lagged signal by return</span><br /><span style="font-style: italic; color: #666666">#if signal is 0 then return is 0 indicating out</span><br />returnComp <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>sp500.ret<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/signal"><span>signal</span></a><span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>*</span>sp500.ret<span style="color: #009900">)</span><br />returnComp<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/is.na"><span style="color: #003399; font-weight: bold">is.na</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #cc66cc">0</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"SP500"</span><span style="color: #339933">,</span><span style="color: #0000ff">"SP500.Faber"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="performance summary.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">7.5</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br />charts.PerformanceSummary<span style="color: #009900">(</span>returnComp<span style="color: #339933">,</span> ylog=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span><br /> colorset=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod3"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"S&amp;P 500 and Mebane Faber Moving Average System<br /> Monthly Performance Since 1950"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#saved this require for later</span><br /><span style="font-style: italic; color: #666666">#since fPortfolio and f anything does not play well</span><br /><span style="font-style: italic; color: #666666">#with PerformanceAnalytics</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/fPortfolio"><span>fPortfolio</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get frontier for the combination</span><br /><span style="font-style: italic; color: #666666">#of the original price and the Faber mov avg system</span><br /><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a> <span>&lt;-</span> portfolioFrontier<span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#most of this comes directly from the fPortfolio demo</span><br /><span style="font-style: italic; color: #666666">#very slight changes have been made</span><br /><span style="font-style: italic; color: #666666">#we will run for the entire period</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="frontier plot.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6, height = 6, units="in",res=96)</span><br /><span style="font-style: italic; color: #666666">#unfortunately title cannot be changed easily</span><br />frontierPlot<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span> pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span> risk = <span style="color: #0000ff">"CVaR"</span><span style="color: #009900">)</span><br />minvariancePoints<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"red"</span><span style="color: #009900">)</span><br />tangencyPoints<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"blue"</span><span style="color: #009900">)</span><br />tangencyLines<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"blue"</span><span style="color: #009900">)</span><br />equalWeightsPoints<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">15</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"grey"</span><span style="color: #009900">)</span><br />singleAssetPoints<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span>cex=<span style="color: #cc66cc">1.5</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod3"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />twoAssetsLines<span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/frontier"><span>frontier</span></a><span style="color: #339933">,</span>lty=<span style="color: #cc66cc">3</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"grey"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"topleft"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a>=<a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod3"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#sharpeRatioLines(frontier,col="orange",lwd=2)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#now let's see what this looks like on a rolling basis</span><br /><span style="font-style: italic; color: #666666">#this from and to is not well documented in the fPortfolio</span><br /><span style="font-style: italic; color: #666666">#documentation so I hope it helps some people</span><br /><span style="font-style: italic; color: #666666">#will use 48 month rolling window and redo every 6 months</span><br /><span style="font-style: italic; color: #666666">#window needs to be large since Faber system will have lots of</span><br /><span style="font-style: italic; color: #666666">#0 returns, which can be handled by adding t-bill returns while out</span><br />from <span>&lt;-</span> rollingWindows<span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #339933">,</span>period=<span style="color: #0000ff">"48m"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/by"><span style="color: #003399; font-weight: bold">by</span></a>=<span style="color: #0000ff">"6m"</span><span style="color: #009900">)</span><span>$</span>from<br />to <span>&lt;-</span> rollingWindows<span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #339933">,</span>period=<span style="color: #0000ff">"48m"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/by"><span style="color: #003399; font-weight: bold">by</span></a>=<span style="color: #0000ff">"6m"</span><span style="color: #009900">)</span><span>$</span>to&nbsp;&nbsp; Spec = portfolioSpec<span style="color: #009900">(</span><span style="color: #009900">)</span><br />setTargetReturn<span style="color: #009900">(</span>Spec<span style="color: #009900">)</span> = <a href="http://inside-r.org/r-doc/base/mean"><span style="color: #003399; font-weight: bold">mean</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/colMeans"><span style="color: #003399; font-weight: bold">colMeans</span></a><span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />Constraints = <span style="color: #0000ff">"LongOnly"</span><br /><span style="font-style: italic; color: #666666">#using Tangency but can also do Cml with rollingCmlPortfolio</span><br /><span style="font-style: italic; color: #666666">#or rollingMinvariancePortfolio</span><br />rollTan <span>&lt;-</span> rollingTangencyPortfolio<span style="color: #009900">(</span>as.timeSeries<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #339933">,</span>Spec<span style="color: #339933">,</span>Constraints<span style="color: #339933">,</span><br /> from=from<span style="color: #339933">,</span>to=to<span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#sapply works very nicely with the lists used in fPortfolio</span><br /><span style="font-style: italic; color: #666666">#get weights from each of the rolling periods</span><br />tanweights <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/sapply"><span style="color: #003399; font-weight: bold">sapply</span></a><span style="color: #009900">(</span>rollTan<span style="color: #339933">,</span>getWeights<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>tanweights<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="rollling weight plot.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/barplot"><span style="color: #003399; font-weight: bold">barplot</span></a><span style="color: #009900">(</span>tanweights<span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod4"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> legend.text=<span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span>names.arg=<a href="http://inside-r.org/r-doc/base/format"><span style="color: #003399; font-weight: bold">format</span></a><span style="color: #009900">(</span>from<span style="color: #339933">,</span><span style="color: #0000ff">"%b %y"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> cex.names=<span style="color: #cc66cc">0.7</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#do not know a slick way to do this</span><br /><span style="font-style: italic; color: #666666">#repeat the weights 6 times for the 6 month by</span><br /><span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>i <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">1</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/t"><span style="color: #003399; font-weight: bold">t</span></a><span style="color: #009900">(</span>tanweights<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <span style="color: #000000; font-weight: bold">for</span> <span style="color: #009900">(</span>j <span style="color: #000000; font-weight: bold">in</span> <span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">6</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <span style="color: #000000; font-weight: bold">if</span> <span style="color: #009900">(</span>i<span>==</span><span style="color: #cc66cc">1</span> <span>&amp;</span> j<span>==</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> tanweights.xts <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/data.frame"><span style="color: #003399; font-weight: bold">data.frame</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/t"><span style="color: #003399; font-weight: bold">t</span></a><span style="color: #009900">(</span>tanweights<span style="color: #009900">[</span><span style="color: #339933">,</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <span style="color: #009900">}</span> <span style="color: #000000; font-weight: bold">else</span> <span style="color: #009900">{</span><br /> <span style="font-style: italic; color: #666666">#check to make sure we do not exceed number</span><br /> <span style="font-style: italic; color: #666666">#of rows in original return series - 48</span><br /> <span style="font-style: italic; color: #666666">#for the initialization</span><br /> <span style="color: #000000; font-weight: bold">if</span> <span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>tanweights.xts<span style="color: #009900">)</span> <span>&lt;=</span> <a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">48</span><span style="color: #009900">)</span><br /> tanweights.xts <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/rbind"><span style="color: #003399; font-weight: bold">rbind</span></a><span style="color: #009900">(</span>tanweights.xts<span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/data.frame"><span style="color: #003399; font-weight: bold">data.frame</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/t"><span style="color: #003399; font-weight: bold">t</span></a><span style="color: #009900">(</span>tanweights<span style="color: #009900">[</span><span style="color: #339933">,</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /> <span style="color: #009900">}</span><br /> <span style="color: #009900">}</span><br /><span style="color: #009900">}</span><br />tanweights.xts <span>&lt;-</span> <a href="http://inside-r.org/packages/cran/xts"><span>xts</span></a><span style="color: #009900">(</span>tanweights.xts<span style="color: #339933">,</span><br /> order.by=index<span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">48</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; tanreturns <span>&lt;-</span> <a href="http://inside-r.org/r-doc/stats/lag"><span style="color: #003399; font-weight: bold">lag</span></a><span style="color: #009900">(</span>tanweights.xts<span style="color: #339933">,</span>k=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span>*</span>returnComp<span style="color: #009900">[</span><span style="color: #cc66cc">49</span><span>:</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #009900">]</span><br />returnComp2 <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/merge"><span style="color: #003399; font-weight: bold">merge</span></a><span style="color: #009900">(</span>returnComp<span style="color: #339933">,</span>tanreturns<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span>+</span>tanreturns<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnComp2<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnComp<span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">2</span><span style="color: #009900">]</span><span style="color: #339933">,</span><span style="color: #0000ff">"Cml"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="risk return.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br />chart.RiskReturnScatter<span style="color: #009900">(</span>returnComp2<span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span><br /><span style="font-style: italic; color: #666666">#since fPortfolio gives error on charts.PerformanceSummary</span><br /><span style="font-style: italic; color: #666666">#assemble quick one-pager</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="perf all.jpg",</span><br /><span style="font-style: italic; color: #666666"># quality=100,width=6, height = 7, units="in",res=96)</span><br /><a href="http://inside-r.org/r-doc/graphics/layout"><span style="color: #003399; font-weight: bold">layout</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/matrix"><span style="color: #003399; font-weight: bold">matrix</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span> height = <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">2.5</span><span style="color: #339933">,</span><span style="color: #cc66cc">1.5</span><span style="color: #009900">)</span><span style="color: #339933">,</span> width = <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/par"><span style="color: #003399; font-weight: bold">par</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/mAr"><span>mar</span></a> = <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <span style="color: #cc66cc">4</span><span style="color: #339933">,</span> <span style="color: #cc66cc">4</span><span style="color: #339933">,</span> <span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />chart.CumReturns<span style="color: #009900">(</span>returnComp2<span style="color: #339933">,</span>xaxis=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span>ylab=<span style="color: #0000ff">"Cumulative Return"</span><span style="color: #339933">,</span><br /> colorset = <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"SP500 with Faber MA and CML Combo"</span><span style="color: #339933">,</span>legend.loc=<span style="color: #0000ff">"topleft"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/par"><span style="color: #003399; font-weight: bold">par</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/mAr"><span>mar</span></a> = <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">5</span><span style="color: #339933">,</span> <span style="color: #cc66cc">4</span><span style="color: #339933">,</span> <span style="color: #cc66cc">0</span><span style="color: #339933">,</span> <span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />chart.Drawdown<span style="color: #009900">(</span>returnComp2<span style="color: #339933">,</span>main=<span style="color: #0000ff">""</span><span style="color: #339933">,</span>ylab=<span style="color: #0000ff">"Drawdown"</span><span style="color: #339933">,</span><br /> colorset=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"lightcyan4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"lightgoldenrod4"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-4430237801073118637?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-16377381279146445432011-09-30T13:54:00.001-07:002011-09-30T13:54:03.104-07:00<p>THIS IS NOT INVESTMENT ADVICE.&nbsp; MY IDEAS PROBABLY WILL LOSE YOU MONEY, AND I WILL NOT LET YOU KNOW WHEN I CHANGE MY MIND.</p> <p>Bloomberg’s article “<a href="http://www.bloomberg.com/news/2011-09-30/asia-currencies-set-for-worst-month-since-97.html">Asian Currencies Set for Worst Month Since 1997 Crisis Caused IMF Bailouts</a>” demonstrates why with all my bearishness I did not make much money this month.&nbsp; Just as a reminder for the not so faithful readers, <a title="http://timelyportfolio.blogspot.com/2011/05/russell-napier-asip-in-ft-says-emerging.html" href="http://timelyportfolio.blogspot.com/2011/05/russell-napier-asip-in-ft-says-emerging.html">http://timelyportfolio.blogspot.com/2011/05/russell-napier-asip-in-ft-says-emerging.html</a> shows why I like long emerging market stocks and short Russell 2000.&nbsp; However, this trade does not work so well when the currencies get clobbered.&nbsp; I understand the clobbering in 1997 when Soros and others had control of the Asian currencies, but 15 years 10 trillion since that crisis, the Asian central banks clearly have control of their currencies if they choose to exert that influence.&nbsp; Billions in outflows are meaningless compared to the trillions sitting in foreign currencies (see post <a href="http://timelyportfolio.blogspot.com/2011/07/join-reserves.html">Join the Reserves</a>), primarily the US $.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/T4w7loFJFIe08t3rj1JRBQ?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-WHn3FLOTsjw/ToYrr4I9P5I/AAAAAAAB1Po/KPycQEXAgwQ/s800/currencies.jpeg" width="666" height="665"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>R code:</p> <p>require(quantmod)<br></p> <p>#get asian currency data from the FED FRED data series<br>getSymbols("DEXKOUS",src="FRED") #load Korea<br>getSymbols("DEXMAUS",src="FRED") #load Malaysia<br>getSymbols("DEXSIUS",src="FRED") #load Singapore<br>getSymbols("DEXTAUS",src="FRED") #load Taiwan<br>getSymbols("DEXCHUS",src="FRED") #load China<br>getSymbols("DEXJPUS",src="FRED") #load Japan<br>getSymbols("DEXTHUS",src="FRED") #load Thailand<br>getSymbols("DEXBZUS",src="FRED") #load Brazil<br>getSymbols("DEXMXUS",src="FRED") #load Mexico<br>getSymbols("DEXINUS",src="FRED") #load India<br>getSymbols("DTWEXO",src="FRED") #load US Dollar Other Trading Partners<br>getSymbols("DTWEXB",src="FRED") #load US Dollar Broad</p> <p>par(mfrow=c(4, 3)) #provides 2 columns and 3 rows for charts<br>plot(1/coredata(DEXKOUS["1995::2011"]),type="l",ylab="Korea")<br>plot(1/coredata(DEXMAUS["1995::2011"]),type="l",ylab="Malaysia")<br>plot(1/coredata(DEXSIUS["1995::2011"]),type="l",ylab="Singapore")<br>plot(1/coredata(DEXTAUS["1995::2011"]),type="l",ylab="Taiwan")<br>plot(1/coredata(DEXCHUS["1995::2011"]),type="l",ylab="China")<br>plot(1/coredata(DEXJPUS["1995::2011"]),type="l",ylab="Japan")<br>plot(1/coredata(DEXTHUS["1995::2011"]),type="l",ylab="Thailand")<br>plot(1/coredata(DEXBZUS["1995::2011"]),type="l",ylab="Brazil")<br>plot(1/coredata(DEXMXUS["1995::2011"]),type="l",ylab="Mexico")<br>plot(1/coredata(DEXINUS["1995::2011"]),type="l",ylab="India")<br>plot(coredata(DTWEXO["1995::2011"]),type="l",ylab="US Dollar Other")<br>plot(coredata(DTWEXB["1995::2011"]),type="l",ylab="US Dollar Broad")</p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-1637738127914644543?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-81360908430282861362011-09-30T13:38:00.001-07:002011-09-30T13:38:13.662-07:00<p>THIS IS NOT INVESTMENT ADVICE.&nbsp; IT IS JUST AN EXAMPLE AND WILL LIKELY LOSE LOTS OF MONEY IF YOU PURSUE WHAT IS DISCUSSED.&nbsp; READER IS RESPONSIBLE FOR THEIR OWN GAINS OR LOSSES.&nbsp; IF YOU ARE AN UNLIKELY WINNER, I WOULD LOVE TO HEAR YOUR STORY. <p>When we are deciding on a quantitative system to guide our investments, we have multiple choices all fraught with potential luck:&nbsp; investment choice, system type, system, timeframe, system parameter or parameters, and money management.&nbsp; To really gain some confidence in the persistence of your choices, I believe each choice should be as rigorously tested as possible.&nbsp; <a href="http://math.uic.edu/~dstjohn/thesis.pdf">http://math.uic.edu/~dstjohn/thesis.pdf</a>, <a title="http://ageconsearch.umn.edu/bitstream/19039/1/cp05pa01.pdf" href="http://ageconsearch.umn.edu/bitstream/19039/1/cp05pa01.pdf">http://ageconsearch.umn.edu/bitstream/19039/1/cp05pa01.pdf</a>, and <a title="http://www.ssc.wisc.edu/~bhansen/718/White2000.pdf" href="http://www.ssc.wisc.edu/~bhansen/718/White2000.pdf">http://www.ssc.wisc.edu/~bhansen/718/White2000.pdf</a> all offer very good discussion of some of the tests.&nbsp; My posts <a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-this-is-test-test-1-and-test-2.html">ttrTests This is a Test--Test 1 and Test 2</a>, <a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-its-great-thesis-and.html">ttrTests: Its Great Thesis and Incredible Potential</a>, and <a href="http://timelyportfolio.blogspot.com/2011/08/ttrtests-experimentation.html">ttrTests Experimentation</a> offer a simple application of the much-less-than-simple statistical tests. <p>I will apply the dataSnoop test with Hansen’s test for Superior Predictive Ability (SPA) to check for luck in the parameter choice of my simple CUD indicator. <p>I hate to do this, but I cannot think of an easy way to describe the output of the dataSnoop test, so I hope you will read <a href="http://math.uic.edu/~dstjohn/thesis.pdf">http://math.uic.edu/~dstjohn/thesis.pdf</a> pages 51-57.&nbsp; Here is the paper’s description of the tests when applied to a MACD system.&nbsp; <a href="http://math.uic.edu/~dstjohn/thesis.pdf"><img style="background-image: none; border-right-width: 0px; padding-left: 0px; padding-right: 0px; display: inline; border-top-width: 0px; border-bottom-width: 0px; border-left-width: 0px; padding-top: 0px" title="clip_image001" border="0" alt="clip_image001" src="http://lh4.ggpht.com/-3nNMa26CNAg/ToYotEDB7uI/AAAAAAAB1Pk/cyZCAUNN3qk/clip_image001%25255B5%25255D.png?imgmax=800" width="600" height="376"></a> <p><a href="http://math.uic.edu/~dstjohn/thesis.pdf">http://math.uic.edu/~dstjohn/thesis.pdf</a> page 55 <p>p-values for my CUD indicator are not so good. <blockquote> <p><font color="#8fb08c">CUD: Observed P-values for Means 'l', 'c', and 'u' respectively: 0.4 0.4 0.97</font></font></p></blockquote> <p><font color="#666666">The observed values from the test are plotted below.</font></p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/iXSHsgsD018UXHs12O0jFQ?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-aXBBK_vZkNI/ToYmtAXtQzI/AAAAAAAB1PY/PoHpv4vpLDg/s800/dataSnoop%252520values.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMzFlZTMyNTUtNjhhZS00NmMyLWI0MGMtOTc5NDEwNjQ4YWQx&amp;hl=en_US">R code (click to download from Google Docs):</a></p> <p>&nbsp;</p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><span style="font-style: italic; color: #666666">#let's define our silly countupdown function</span><br /><span style="font-style: italic; color: #666666">#as a sample of a custom ttr rule</span><br />CUD <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/function"><span style="color: #003399; font-weight: bold">function</span></a><span style="color: #009900">(</span>x<span style="color: #339933">,</span>params=<span style="color: #cc66cc">50</span><span style="color: #339933">,</span>...<span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <span style="font-style: italic; color: #666666">#CUD takes the n-period sum of 1 (up days) and -1 (down days)</span><br /> temp <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>runSum<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>ROC<span style="color: #009900">(</span>x<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span>-</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span>params<span style="color: #009900">)</span><span>&gt;=</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">0</span><span style="color: #009900">)</span><br /> <span style="font-style: italic; color: #666666">#replace NA with 0 at beginning of period</span><br /> temp<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/is.na"><span style="color: #003399; font-weight: bold">is.na</span></a><span style="color: #009900">(</span>temp<span style="color: #009900">)</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #cc66cc">0</span><br /> temp<br /><span style="color: #009900">}</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/ttrTests"><span>ttrTests</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/lattice"><span>lattice</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span>reshape2<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#defaults functions is overridden by ggplot2 and plyr if loaded</span><br /><span style="font-style: italic; color: #666666">#and will cause problems if you want to use ttrTests concurrently</span>&nbsp;&nbsp; tckrs <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"GSPC"</span><span style="color: #339933">,</span><span style="color: #0000ff">"RUT"</span><span style="color: #339933">,</span><span style="color: #0000ff">"N225"</span><span style="color: #339933">,</span><span style="color: #0000ff">"GDAXI"</span><span style="color: #339933">,</span><span style="color: #0000ff">"DJUBS"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#use 1 or GSPC but adjust however you would like</span><br />i=<span style="color: #cc66cc">1</span><br />getSymbols<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"^"</span><span style="color: #339933">,</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span>to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />test_price <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.vector"><span style="color: #003399; font-weight: bold">as.vector</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/get"><span style="color: #003399; font-weight: bold">get</span></a><span style="color: #009900">(</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#run dataSnoop to test for luck</span><br /><span style="font-style: italic; color: #666666">#by checking all parameters across multiple bootstrap samples</span><br /><span style="font-style: italic; color: #666666">#this takes a long time, so for experimenting change bSamples to</span><br /><span style="font-style: italic; color: #666666">#something smaller than 100</span><br /><span style="font-style: italic; color: #666666">#if you are planning to use this for commercial purposes</span><br /><span style="font-style: italic; color: #666666">#make sure you see the warning in the documentation</span><br /><span style="font-style: italic; color: #666666">#on Dr. Halbert White's patent and his paper</span><br /><span style="font-style: italic; color: #666666">#http://www.ssc.wisc.edu/~bhansen/718/White2000.pdf</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#don't get me started on patents of this sort</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#crit can be "sharpe", "return", or "adjust"</span><br /><span style="font-style: italic; color: #666666">#will choose "sharpe" but feel free to try them all</span><br />snoop <span>&lt;-</span> dataSnoop<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a> = CUD<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/stats/start"><span style="color: #003399; font-weight: bold">start</span></a> = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> nSteps = <span style="color: #cc66cc">30</span><span style="color: #339933">,</span> stepSize = <span style="color: #cc66cc">10</span><span style="color: #339933">,</span><br /> bSamples=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span> crit=<span style="color: #0000ff">"sharpe"</span><span style="color: #339933">,</span><br /> restrict = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> burn = <span style="color: #cc66cc">0</span><span style="color: #339933">,</span> short = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> condition = <span style="color: #000000; font-weight: bold">NULL</span><span style="color: #339933">,</span><br /> silent = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> TC = <span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> loud = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> alpha = <span style="color: #cc66cc">0.025</span><span style="color: #339933">,</span><br /> begin = <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> percent = <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a> = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> benchmark = <span style="color: #0000ff">"hold"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>snoop<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"details"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V2"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"V3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p1.for.l"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p2.for.c"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p3.for.u"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="dataSnoop values.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>snoop<span>$</span>V3<span style="color: #339933">,</span><br /> type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">2</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"ttrTests dataSnoop V1,V2,and V3 on CUD"</span><span style="color: #339933">,</span><br /> xlab=<span style="color: #0000ff">"Bootstrap Sample"</span><span style="color: #339933">,</span> ylab=<span style="color: #0000ff">"Values"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>snoop<span>$</span>V2<span style="color: #339933">,</span> type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">3</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/points"><span style="color: #003399; font-weight: bold">points</span></a><span style="color: #009900">(</span>snoop<span>$</span>V1<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #cc66cc">4</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"topright"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/graphics/legend"><span style="color: #003399; font-weight: bold">legend</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"V1"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V2"</span><span style="color: #339933">,</span><span style="color: #0000ff">"V3"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">4</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span style="color: #009900">)</span><span style="color: #339933">,</span>pch=<span style="color: #cc66cc">19</span><span style="color: #339933">,</span>lty=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-8136090843028286136?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-26879902692527334922011-09-28T21:05:00.001-07:002011-09-28T21:05:23.499-07:00<p>Just to remind everyone, THIS IS NOT INVESTMENT ADVICE AND ANY ACTIONS TAKEN BASED ON THIS DISCUSSION WILL PROBABLY RESULT IN SIGNIFICANT LOSSES.</p> <p>We had fun with the ttrTests package in two previous posts <a href="http://timelyportfolio.blogspot.com/2011/09/ttrtests-its-great-thesis-and.html">ttrTests: Its Great Thesis and Incredible Potential</a> and <a href="http://timelyportfolio.blogspot.com/2011/08/ttrtests-experimentation.html">ttrTests Experimentation</a>.&nbsp; Let’s actually run some real tests on the basic CUD indicator introduced in <a href="http://timelyportfolio.blogspot.com/2011/07/quantstrat-to-build-on-part-6.html">A Quantstrat to Build On Part 6</a>.&nbsp; We will start by using paramStats to test multiple parameters.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/G5wB62rwtG6Eyn70noNUpw?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-rmMy-fZ-oB8/ToPpXtYW6OI/AAAAAAAB1PA/t2K6AAUsdhg/s800/excess%252520by%252520parameter.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>After we find the best parameter, we will test with returnStats the actual returns using the best parameter for the CUD indicator versus a buy-and-hold approach.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/xmktSMx0VN87js_XnHDghQ?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-a4FAoXXCOig/ToPpXS8rC7I/AAAAAAAB1O4/M0vFgR1u-oA/s800/analysis%252520of%252520returns.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>Finally, we will try to apply some statistical rigidity to the process by using 100 bootstrapped samples to test the best parameter on out-of-sample data. As always, please let me know your thoughts.</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/n1jOi_GunZJJZp2JfZrWHQ?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-BoY8q36cnyA/ToPpX8yd9WI/AAAAAAAB1PE/CLZi-aVzGzQ/s800/excess%252520return%252520by%252520bootstrap.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/JB0g2v8iDkGH2so61YAgZA?feat=embedwebsite"><img src="https://lh5.googleusercontent.com/-ogyrKbJmjpE/ToPpXsSDk9I/AAAAAAAB1O8/VvJMBYuzw8A/s800/excess%252520adjusted%252520return%252520by%252520bootstrap.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/5lOwvju5YAnrg-FFGuYBmg?feat=embedwebsite"><img src="https://lh4.googleusercontent.com/-taL9UXQhvYY/ToPpYEc456I/AAAAAAAB1PI/voB-Q9a1OVY/s800/excess%252520sharpe%252520ratio%252520by%252520bootstrap.jpg" width="600" height="600"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMjFjYWVlZDgtMzIxMi00ZDUwLWJjZTQtNzEzMmVmYWE1NDg5&amp;hl=en_US">R code (click to download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><span style="font-style: italic; color: #666666">#let's define our silly countupdown function</span><br /><span style="font-style: italic; color: #666666">#as a sample of a custom ttr rule</span><br />CUD <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/function"><span style="color: #003399; font-weight: bold">function</span></a><span style="color: #009900">(</span>x<span style="color: #339933">,</span>params=<span style="color: #cc66cc">50</span><span style="color: #339933">,</span>...<span style="color: #009900">)</span> <span style="color: #009900">{</span><br /> <span style="font-style: italic; color: #666666">#CUD takes the n-period sum of 1 (up days) and -1 (down days)</span><br /> temp <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>runSum<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/ifelse"><span style="color: #003399; font-weight: bold">ifelse</span></a><span style="color: #009900">(</span>ROC<span style="color: #009900">(</span>x<span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span>type=<span style="color: #0000ff">"discrete"</span><span style="color: #009900">)</span> <span>&gt;</span> <span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span>-</span><span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #339933">,</span>params<span style="color: #009900">)</span><span>&gt;=</span><span style="color: #cc66cc">0</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">0</span><span style="color: #009900">)</span><br /> <span style="font-style: italic; color: #666666">#replace NA with 0 at beginning of period</span><br /> temp<span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/is.na"><span style="color: #003399; font-weight: bold">is.na</span></a><span style="color: #009900">(</span>temp<span style="color: #009900">)</span><span style="color: #009900">]</span> <span>&lt;-</span> <span style="color: #cc66cc">0</span><br /> temp<br /><span style="color: #009900">}</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/ttrTests"><span>ttrTests</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/lattice"><span>lattice</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span>reshape2<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#defaults functions is overridden by ggplot2 and plyr if loaded</span><br /><span style="font-style: italic; color: #666666">#and will cause problems if you want to use ttrTests concurrently</span>&nbsp;&nbsp; tckrs <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"GSPC"</span><span style="color: #339933">,</span><span style="color: #0000ff">"RUT"</span><span style="color: #339933">,</span><span style="color: #0000ff">"N225"</span><span style="color: #339933">,</span><span style="color: #0000ff">"GDAXI"</span><span style="color: #339933">,</span><span style="color: #0000ff">"DJUBS"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#use 1 or GSPC but adjust however you would like</span><br />i=<span style="color: #cc66cc">1</span><br />getSymbols<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"^"</span><span style="color: #339933">,</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span>to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br />test_price <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.vector"><span style="color: #003399; font-weight: bold">as.vector</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/get"><span style="color: #003399; font-weight: bold">get</span></a><span style="color: #009900">(</span>tckrs<span style="color: #009900">[</span>i<span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#do parameter tests but plot=FALSE</span><br /><span style="font-style: italic; color: #666666">#we will plot later</span><br />param_results <span>&lt;-</span> paramStats<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a> = CUD<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/stats/start"><span style="color: #003399; font-weight: bold">start</span></a> = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> nSteps = <span style="color: #cc66cc">30</span><span style="color: #339933">,</span> stepSize = <span style="color: #cc66cc">10</span><span style="color: #339933">,</span><br /> restrict = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> burn = <span style="color: #cc66cc">0</span><span style="color: #339933">,</span> short = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> condition = <span style="color: #000000; font-weight: bold">NULL</span><span style="color: #339933">,</span><br /> silent = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> TC = <span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> loud = <span style="color: #000000; font-weight: bold">TRUE</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a> = <span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> alpha = <span style="color: #cc66cc">0.025</span><span style="color: #339933">,</span><br /> begin = <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> percent = <span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/file"><span style="color: #003399; font-weight: bold">file</span></a> = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> benchmark = <span style="color: #0000ff">"hold"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>param_results<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"excess.return"</span><span style="color: #339933">,</span><span style="color: #0000ff">"z.score"</span><span style="color: #339933">,</span><span style="color: #0000ff">"adj.excess.return"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"Sharpe.ratio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best.repeat"</span><span style="color: #339933">,</span><span style="color: #0000ff">"best.adjusted"</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"tested.parameters"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>param_results<span style="color: #009900">)</span><span>-</span><span style="color: #cc66cc">7</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="excess by parameter.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>param_results<span>$</span>excess.return<span>~</span>param_results<span>$</span>tested.parameters1<span style="color: #339933">,</span><br /> type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"darkgray"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"ttrTests Excess Return by Parameter"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>v=param_results<span>$</span>best<span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred3"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#let's use the returnStats function to get</span><br /><span style="font-style: italic; color: #666666">#more complete return and distribution info on the best parameter</span><br /><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a> <span>&lt;-</span> returnStats<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a>=CUD<span style="color: #339933">,</span> params=param_results<span>$</span>best<span style="color: #339933">,</span><br /> short=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> TC=<span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> benchmark=<span style="color: #0000ff">"hold"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"benchmark.stats"</span><span style="color: #339933">,</span><span style="color: #0000ff">"ttr.stats"</span><span style="color: #339933">,</span><span style="color: #0000ff">"adj.stats.and.periods"</span><span style="color: #339933">,</span><br /> <span style="color: #0000ff">"excess.stats"</span><span style="color: #339933">,</span><span style="color: #0000ff">"long.stats"</span><span style="color: #339933">,</span><span style="color: #0000ff">"short.stats"</span><span style="color: #339933">,</span><span style="color: #0000ff">"neutral.stats"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="analysis of returns.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/barplot"><span style="color: #003399; font-weight: bold">barplot</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>long.stats<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>short.stats<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>neutral.stats<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>benchmark.stats<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"indianred3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"steelblue3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"gray70"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> names.arg=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"long"</span><span style="color: #339933">,</span><span style="color: #0000ff">"short"</span><span style="color: #339933">,</span><span style="color: #0000ff">"neutral"</span><span style="color: #339933">,</span><span style="color: #0000ff">"benchmark"</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Analysis of Returns from ttrTests"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#now let's test the best parameter with nullModel</span><br /><span style="font-style: italic; color: #666666">#this tests the parameter with bootstrap resampling</span><br /><span style="font-style: italic; color: #666666">#for significance across one of three criteria</span><br /><span style="font-style: italic; color: #666666">#specified by crit = "sharpe", "return" (excess return),</span><br /><span style="font-style: italic; color: #666666">#or "adjust" (excess adjusted for trading costs)</span><br />nmodel <span>&lt;-</span> nullModel<span style="color: #009900">(</span>x=test_price<span style="color: #339933">,</span> model=<span style="color: #0000ff">"stationaryBootstrap"</span><span style="color: #339933">,</span> userParams=<span style="color: #cc66cc">4</span><span style="color: #339933">,</span> bSamples=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span><br /> <a href="http://inside-r.org/packages/cran/TTR"><span>ttr</span></a>=CUD<span style="color: #339933">,</span> params=param_results<span>$</span>best<span style="color: #339933">,</span> short=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #339933">,</span> TC=<span style="color: #cc66cc">0.001</span><span style="color: #339933">,</span> crit=<span style="color: #0000ff">"sharpe"</span><span style="color: #339933">,</span><br /> benchmark=<span style="color: #0000ff">"hold"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#make output slightly more usable with some naming</span><br /><span style="font-style: italic; color: #666666">#believe I got this right</span><br /><span style="font-style: italic; color: #666666">#this is different from documentation but code seems to</span><br /><span style="font-style: italic; color: #666666">#fit with this</span><br /><a href="http://inside-r.org/r-doc/base/names"><span style="color: #003399; font-weight: bold">names</span></a><span style="color: #009900">(</span>nmodel<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"excess.return"</span><span style="color: #339933">,</span><span style="color: #0000ff">"excess.Sharpe.ratio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"adj.excess.return"</span><span style="color: #339933">,</span><span style="color: #0000ff">"p.value"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#jpeg(filename="excess return by bootstrap.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>nmodel<span>$</span>excess.return<span style="color: #339933">,</span>type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span>xlab=<span style="color: #0000ff">"Bootstrap Sample"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Excess Return for each Bootstrapped Sample"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#add line for excess return from actual ttr performance</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>h=<a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>excess.stats<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred3"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="excess adjusted return by bootstrap.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>nmodel<span>$</span>adj.excess.return<span style="color: #339933">,</span>type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"khaki4"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Excess Adjusted Return for each Bootstrapped Sample"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#add line for excess adjusted from actual ttr performance</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>h=<a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>adj.stats.and.periods<span style="color: #009900">[</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred3"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="excess sharpe ratio by bootstrap.jpg",</span><br /> quality=<span style="color: #cc66cc">100</span><span style="color: #339933">,</span>width=<span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> height = <span style="color: #cc66cc">6.25</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/units"><span style="color: #003399; font-weight: bold">units</span></a>=<span style="color: #0000ff">"in"</span><span style="color: #339933">,</span>res=<span style="color: #cc66cc">96</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/graphics/plot"><span style="color: #003399; font-weight: bold">plot</span></a><span style="color: #009900">(</span>nmodel<span>$</span>excess.Sharpe.ratio<span style="color: #339933">,</span>type=<span style="color: #0000ff">"l"</span><span style="color: #339933">,</span>lwd=<span style="color: #cc66cc">2</span><span style="color: #339933">,</span>xlab=<span style="color: #0000ff">"BootstrapSample"</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"cadetblue4"</span><span style="color: #339933">,</span><br /> main=<span style="color: #0000ff">"Excess Sharpe Ratio for each Bootstrapped Sample"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#add line for excess sharpe from actual ttr performance</span><br /><a href="http://inside-r.org/r-doc/graphics/abline"><span style="color: #003399; font-weight: bold">abline</span></a><span style="color: #009900">(</span>h=<a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>ttr.stats<span style="color: #009900">[</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span>-</span><a href="http://inside-r.org/r-doc/stats"><span style="color: #006600; font-weight: bold">stats</span></a><span>$</span>benchmark.stats<span style="color: #009900">[</span><span style="color: #cc66cc">3</span><span style="color: #009900">]</span><span style="color: #339933">,</span> <a href="http://inside-r.org/r-doc/base/col"><span style="color: #003399; font-weight: bold">col</span></a>=<span style="color: #0000ff">"indianred3"</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2687990269252733492?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com0tag:blogger.com,1999:blog-7630810606654250077.post-25188214698660411492011-09-26T15:22:00.001-07:002011-09-26T15:22:59.123-07:00<p>I stumbled on the ttrTests R package as mentioned in my post <a href="http://timelyportfolio.blogspot.com/2011/08/ttrtests-experimentation.html">ttrTests Experimentation</a>.&nbsp; I did not recognize its potential until I spent much more time absorbing the basis of the package—David St. John’s thesis <a href="http://math.uic.edu/~dstjohn/thesis.pdf">Technical Analysis Based on Moving Average Convergence and Divergence</a>.&nbsp; Since the title specifically addresses MACD, which I have had little luck implementing, I dismissed much of the content.&nbsp; However, the power of the thesis extends well beyond MACD to all systematic methods and describes tests to ensure luck is not the source of a system’s returns.&nbsp; In the package documentation, there is a summary of the 5 main tests:</p> <blockquote> <p>“Contains five major tests supported by other functions: Did the TTR strategy outperform a benchmark in the past data? Is the excess return significant, using bootstrapping to construct a confidence interval? Is the excess return explained by data snooping? Is the ’good’ choice of parameters robust across sub-samples? Is this robustness significant, using bootstrapping to construct a confidence interval?”</p></blockquote> <p>The tests expose luck, data snooping, trading costs, and parameter persistence across both degrees of freedom and subperiods.&nbsp; I look forward to documenting its power in my blog and also potentially working with the author to include in other R packages such as quantstrat.</p> <p>Since I am running out of time, I first want to apply each of the tests to MACD in the same style as the package documentation and the thesis paper, but this time on a xts DJI object gathered through getSymbols rather than the spData provided with the package.</p> <p>The output from the tests is very cumbersome, but I hope this set of examples will help provide a flavor for the package and its powerful tests.&nbsp; In my next couple of posts, I will run each test in much further detail on my basic custom CUD indicator and try to get the cumbersome output in a far more digestible and graphical format.</p> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMDZjNjA3M2UtNDI2OS00NTRjLTg3ZjgtNzVlY2MxZDEzMmUz&amp;hl=en_US">R code (click to download from Google Docs):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/ttrTests"><span>ttrTests</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#get Dow Jones Industrials from Yahoo! Finance</span><br />getSymbols<span style="color: #009900">(</span><span style="color: #0000ff">"^DJI"</span><span style="color: #339933">,</span>from=<span style="color: #0000ff">"1896-01-01"</span><span style="color: #339933">,</span>to=<a href="http://inside-r.org/r-doc/base/Sys.Date"><span style="color: #003399; font-weight: bold">Sys.Date</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#convert closing price to vector format which works best with ttrTests</span><br />DJI.vector <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/as.vector"><span style="color: #003399; font-weight: bold">as.vector</span></a><span style="color: #009900">(</span>DJI<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">4</span><span style="color: #009900">]</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#using the defaults as mentioned in the thesis paper on MACD</span><br /><span style="font-style: italic; color: #666666">#show each of the tests in order of their mention</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#quotes are from ttrTests package documentation</span><br /><span style="font-style: italic; color: #666666">#"compares the performance of the TTR with some benchmark"</span><br />returnStats<span style="color: #009900">(</span>DJI.vector<span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#"constructs a confidence interval for this performance"</span><br /><span style="font-style: italic; color: #666666">#"and gives a p-value for the excess return observed in (1)."</span><br />nullModel<span style="color: #009900">(</span>DJI.vector<span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#"constructs a p-value for the ’best’ choice"</span><br /><span style="font-style: italic; color: #666666">#"of parameters within a given domain"</span><br />dataSnoop<span style="color: #009900">(</span>DJI.vector<span style="color: #339933">,</span>bSamples=<span style="color: #cc66cc">3</span><span style="color: #339933">,</span>test=<span style="color: #0000ff">"RC"</span><span style="color: #009900">)</span><br />dataSnoop<span style="color: #009900">(</span>DJI.vector<span style="color: #339933">,</span>bSamples=<span style="color: #cc66cc">3</span><span style="color: #339933">,</span>test=<span style="color: #0000ff">"SPA"</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#"asks whether or not good choices of parameters"</span><br /><span style="font-style: italic; color: #666666">#"were robust across different time periods"</span><br /><span style="font-style: italic; color: #666666">#chose 8 since data is from 1928 will approximate by decade</span><br />subperiods<span style="color: #009900">(</span>DJI.vector<span style="color: #339933">,</span> periods=<span style="color: #cc66cc">8</span><span style="color: #009900">)</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#and my favorite of all</span><br /><span style="font-style: italic; color: #666666">#"tests if the persistence measure from subperiods()"</span><br /><span style="font-style: italic; color: #666666">#"is statistically significant"</span><br /><span style="font-style: italic; color: #666666">#this takes the longest (about 10 minutes on my i7 laptop)</span><br />paramPersist<span style="color: #009900">(</span>DJI.vector<span style="color: #009900">)</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2518821469866041149?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com2tag:blogger.com,1999:blog-7630810606654250077.post-28753518577362501982011-09-16T07:30:00.001-07:002011-09-16T07:30:37.771-07:00<p>Now after <a href="http://timelyportfolio.blogspot.com/2011/09/reporting-good-enough-to-share.html">Reporting Good Enough to Share</a>, let’s use ggplot2 and PerformanceAnalytics to turn this</p> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMzBmNjQzZTgtMzFjNy00MDkwLTg0Y2EtOTQyMWM3NTZiYjY3&amp;hl=en_US"><img style="background-image: none; border-right-width: 0px; padding-left: 0px; padding-right: 0px; display: inline; border-top-width: 0px; border-bottom-width: 0px; border-left-width: 0px; padding-top: 0px" title="image4" border="0" alt="image4" src="http://lh3.ggpht.com/-zC1QuWeS4hE/TnNdjNv7FQI/AAAAAAAB1EM/0axgV8PmsqY/image4%25255B3%25255D.png?imgmax=800" width="381" height="98"></a> </p> <p>into this</p> <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/1rlVyNw9ycy21pGeNHOBLA?feat=embedwebsite"><img src="https://lh6.googleusercontent.com/-3vDCZ529BM0/TnNbpkWwuTI/AAAAAAAB1EA/gqDePzyP5SA/s800/performance%252520ggplot.jpg" width="624" height="768"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>I have been notified that the colors aren’t great.&nbsp; How does everyone like this?</p> <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPZTk3OWI1NTItMWQyZS00ZjAwLWFiZWEtODNiNjc0YjIzYzQ3&amp;hl=en_US">R code (click to download):</a></p> <div style="overflow: auto"> <div class="geshifilter"><pre style="font-family: monospace" class="r geshifilter-R"><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/quantmod"><span>quantmod</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/ggplot2"><span>ggplot2</span></a><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/require"><span style="color: #003399; font-weight: bold">require</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/packages/cran/PerformanceAnalytics"><span>PerformanceAnalytics</span></a><span style="color: #009900">)</span>&nbsp;&nbsp; clientPerf <span>&lt;-</span> <a href="http://inside-r.org/r-doc/utils/read.csv"><span style="color: #003399; font-weight: bold">read.csv</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"clientperf.csv"</span><span style="color: #339933">,</span>stringsAsFactors=<span style="color: #000000; font-weight: bold">FALSE</span><span style="color: #009900">)</span><br />clientPerf<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">]</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/lapply"><span style="color: #003399; font-weight: bold">lapply</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/as.numeric"><span style="color: #003399; font-weight: bold">as.numeric</span></a><span style="color: #009900">)</span><br />clientPerf <span>&lt;-</span> as.xts<span style="color: #009900">(</span>clientPerf<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">2</span><span>:</span><a href="http://inside-r.org/r-doc/base/NCOL"><span style="color: #003399; font-weight: bold">NCOL</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">]</span><span>/</span><span style="color: #cc66cc">100</span><span style="color: #339933">,</span><br /> order.by = <a href="http://inside-r.org/r-doc/base/as.Date"><span style="color: #003399; font-weight: bold">as.Date</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">[</span><span style="color: #339933">,</span><span style="color: #cc66cc">1</span><span style="color: #009900">]</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/format"><span style="color: #003399; font-weight: bold">format</span></a>=<span style="color: #0000ff">"%m-%d-%y"</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Client"</span><span style="color: #339933">,</span><span style="color: #0000ff">"BarclaysAgg"</span><span style="color: #339933">,</span><span style="color: #0000ff">"SP500"</span><span style="color: #009900">)</span>&nbsp;&nbsp;&nbsp;&nbsp; returns.cumul <span>&lt;-</span> <a href="http://inside-r.org/packages/cran/xts"><span>xts</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/apply"><span style="color: #003399; font-weight: bold">apply</span></a><span style="color: #009900">(</span><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>+</span>clientPerf<span style="color: #009900">)</span><span style="color: #339933">,</span>MARGIN=<span style="color: #cc66cc">2</span><span style="color: #339933">,</span>FUN=<a href="http://inside-r.org/r-doc/base/cumprod"><span style="color: #003399; font-weight: bold">cumprod</span></a><span style="color: #009900">)</span><span style="color: #339933">,</span>order.by=index<span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">)</span><br />returns.cumul.Melt <span>&lt;-</span> melt<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/as.data.frame"><span style="color: #003399; font-weight: bold">as.data.frame</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span>index<span style="color: #009900">(</span>returns.cumul<span style="color: #009900">)</span><span style="color: #339933">,</span><br /> coredata<span style="color: #009900">(</span>returns.cumul<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span>id.vars=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returns.cumul.Melt<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Date"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Portfolio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Growth"</span><span style="color: #009900">)</span><br />a<span>&lt;-</span><a href="http://inside-r.org/packages/cran/ggplot"><span>ggplot</span></a><span style="color: #009900">(</span>returns.cumul.Melt<span style="color: #339933">,</span>stat=<span style="color: #0000ff">"identity"</span><span style="color: #339933">,</span><br /> aes<span style="color: #009900">(</span>x=<a href="http://inside-r.org/packages/cran/date"><span>Date</span></a><span style="color: #339933">,</span>y=Growth<span style="color: #339933">,</span>colour=<a href="http://inside-r.org/packages/cran/portfolio"><span>Portfolio</span></a><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> geom_line<span style="color: #009900">(</span>lwd=<span style="color: #cc66cc">1</span><span style="color: #009900">)</span> <span>+</span> <br /> scale_x_date<span style="color: #009900">(</span><span style="color: #009900">)</span> <span>+</span><br /> scale_colour_manual<span style="color: #009900">(</span>values=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"cadetblue"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"gray70"</span><span style="color: #339933">,</span><span style="color: #0000ff">"bisque3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"purple"</span><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> theme_bw<span style="color: #009900">(</span><span style="color: #009900">)</span> <span>+</span> <br /> labs<span style="color: #009900">(</span>x = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> y = <span style="color: #0000ff">""</span><span style="color: #009900">)</span> <span>+</span><br /> opts<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/graphics/title"><span style="color: #003399; font-weight: bold">title</span></a> = <span style="color: #0000ff">"Cumulative Returns"</span><span style="color: #339933">,</span>plot.title = theme_text<span style="color: #009900">(</span>size = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> hjust = <span style="color: #cc66cc">0</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; returnTable <span>&lt;-</span> table.TrailingPeriods<span style="color: #009900">(</span>clientPerf<span style="color: #339933">,</span><br /> periods=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">12</span><span style="color: #339933">,</span><span style="color: #cc66cc">24</span><span style="color: #339933">,</span><span style="color: #cc66cc">36</span><span style="color: #339933">,</span><a href="http://inside-r.org/r-doc/base/NROW"><span style="color: #003399; font-weight: bold">NROW</span></a><span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #339933">,</span><br /> FUNCS=<span style="color: #0000ff">"Return.annualized"</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>returnTable<span style="color: #009900">)</span> <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/paste"><span style="color: #003399; font-weight: bold">paste</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span>:</span><span style="color: #cc66cc">3</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">" Year"</span><span style="color: #339933">,</span>sep=<span style="color: #0000ff">""</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #0000ff">"Since Inception"</span><span style="color: #009900">)</span><br />returnMelt <span>&lt;-</span> melt<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>returnTable<span style="color: #009900">)</span><span style="color: #339933">,</span>returnTable<span>*</span><span style="color: #cc66cc">100</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>returnMelt<span style="color: #009900">)</span><span>&lt;-</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Period"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Portfolio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Value"</span><span style="color: #009900">)</span><br />b<span>&lt;-</span><a href="http://inside-r.org/packages/cran/ggplot"><span>ggplot</span></a><span style="color: #009900">(</span>returnMelt<span style="color: #339933">,</span> stat=<span style="color: #0000ff">"identity"</span><span style="color: #339933">,</span> <br /> aes<span style="color: #009900">(</span>x=Period<span style="color: #339933">,</span>y=Value<span style="color: #339933">,</span>fill=<a href="http://inside-r.org/packages/cran/portfolio"><span>Portfolio</span></a><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> geom_bar<span style="color: #009900">(</span>position=<span style="color: #0000ff">"dodge"</span><span style="color: #009900">)</span> <span>+</span><br /> scale_fill_manual<span style="color: #009900">(</span>values=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"cadetblue"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"gray70"</span><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> theme_bw<span style="color: #009900">(</span><span style="color: #009900">)</span> <span>+</span> <br /> labs<span style="color: #009900">(</span>x = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> y = <span style="color: #0000ff">""</span><span style="color: #009900">)</span> <span>+</span> <br /> opts<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/graphics/title"><span style="color: #003399; font-weight: bold">title</span></a> = <span style="color: #0000ff">"Returns (annualized)"</span><span style="color: #339933">,</span>plot.title = theme_text<span style="color: #009900">(</span>size = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> hjust = <span style="color: #cc66cc">0</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp;&nbsp;&nbsp; downsideTable<span>&lt;-</span>table.DownsideRisk<span style="color: #009900">(</span>clientPerf<span style="color: #009900">)</span><span style="color: #009900">[</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span><span style="color: #cc66cc">5</span><span style="color: #339933">,</span><span style="color: #cc66cc">7</span><span style="color: #339933">,</span><span style="color: #cc66cc">8</span><span style="color: #009900">)</span><span style="color: #339933">,</span><span style="color: #009900">]</span><br />downsideMelt<span>&lt;-</span>melt<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/cbind"><span style="color: #003399; font-weight: bold">cbind</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/rownames"><span style="color: #003399; font-weight: bold">rownames</span></a><span style="color: #009900">(</span>downsideTable<span style="color: #009900">)</span><span style="color: #339933">,</span><br /> downsideTable<span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/colnames"><span style="color: #003399; font-weight: bold">colnames</span></a><span style="color: #009900">(</span>downsideMelt<span style="color: #009900">)</span><span>&lt;-</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"Statistic"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Portfolio"</span><span style="color: #339933">,</span><span style="color: #0000ff">"Value"</span><span style="color: #009900">)</span><br />c<span>&lt;-</span><a href="http://inside-r.org/packages/cran/ggplot"><span>ggplot</span></a><span style="color: #009900">(</span>downsideMelt<span style="color: #339933">,</span> stat=<span style="color: #0000ff">"identity"</span><span style="color: #339933">,</span> <br /> aes<span style="color: #009900">(</span>x=Statistic<span style="color: #339933">,</span>y=Value<span style="color: #339933">,</span>fill=<a href="http://inside-r.org/packages/cran/portfolio"><span>Portfolio</span></a><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> geom_bar<span style="color: #009900">(</span>position=<span style="color: #0000ff">"dodge"</span><span style="color: #009900">)</span> <span>+</span> coord_flip<span style="color: #009900">(</span><span style="color: #009900">)</span> <span>+</span><br /> scale_fill_manual<span style="color: #009900">(</span>values=<a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #009900">(</span><span style="color: #0000ff">"cadetblue"</span><span style="color: #339933">,</span><span style="color: #0000ff">"darkolivegreen3"</span><span style="color: #339933">,</span><span style="color: #0000ff">"gray70"</span><span style="color: #009900">)</span><span style="color: #009900">)</span> <span>+</span><br /> theme_bw<span style="color: #009900">(</span><span style="color: #009900">)</span> <span>+</span> <br /> labs<span style="color: #009900">(</span>x = <span style="color: #0000ff">""</span><span style="color: #339933">,</span> y = <span style="color: #0000ff">""</span><span style="color: #009900">)</span> <span>+</span><br /> opts<span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/graphics/title"><span style="color: #003399; font-weight: bold">title</span></a> = <span style="color: #0000ff">"Risk Measures"</span><span style="color: #339933">,</span>plot.title = theme_text<span style="color: #009900">(</span>size = <span style="color: #cc66cc">20</span><span style="color: #339933">,</span> hjust = <span style="color: #cc66cc">0</span><span style="color: #009900">)</span><span style="color: #009900">)</span> <br /> <span style="font-style: italic; color: #666666">#geom_hline(aes(y = 0))</span><br /> <span style="font-style: italic; color: #666666">#opts(axis.line = theme_segment(colour = "red"))</span><br /> <span style="font-style: italic; color: #666666">#opts(panel.grid.major = theme_line(linetype = "dotted"))</span>&nbsp;&nbsp; <span style="font-style: italic; color: #666666">#jpeg(filename="performance ggplot.jpg",quality=100,width=6.5, height = 8, units="in",res=96)</span><br /><span style="font-style: italic; color: #666666">#pdf("perf ggplot.pdf", width = 8.5, height = 11)</span>&nbsp;&nbsp; <a href="http://inside-r.org/r-doc/grid/grid.newpage"><span style="color: #003399; font-weight: bold">grid.newpage</span></a><span style="color: #009900">(</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/grid/pushViewport"><span style="color: #003399; font-weight: bold">pushViewport</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/grid/viewport"><span style="color: #003399; font-weight: bold">viewport</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/graphics/layout"><span style="color: #003399; font-weight: bold">layout</span></a> = <a href="http://inside-r.org/r-doc/grid/grid.layout"><span style="color: #003399; font-weight: bold">grid.layout</span></a><span style="color: #009900">(</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><span style="color: #009900">)</span>&nbsp;&nbsp; vplayout <span>&lt;-</span> <a href="http://inside-r.org/r-doc/base/function"><span style="color: #003399; font-weight: bold">function</span></a><span style="color: #009900">(</span>x<span style="color: #339933">,</span> y<span style="color: #009900">)</span> <br /> <a href="http://inside-r.org/r-doc/grid/viewport"><span style="color: #003399; font-weight: bold">viewport</span></a><span style="color: #009900">(</span>layout.pos.row = x<span style="color: #339933">,</span> layout.pos.col = y<span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/print"><span style="color: #003399; font-weight: bold">print</span></a><span style="color: #009900">(</span>a<span style="color: #339933">,</span> vp = vplayout<span style="color: #009900">(</span><span style="color: #cc66cc">1</span><span style="color: #339933">,</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/print"><span style="color: #003399; font-weight: bold">print</span></a><span style="color: #009900">(</span>b<span style="color: #339933">,</span> vp = vplayout<span style="color: #009900">(</span><span style="color: #cc66cc">2</span><span style="color: #339933">,</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><a href="http://inside-r.org/r-doc/base/print"><span style="color: #003399; font-weight: bold">print</span></a><span style="color: #009900">(</span><a href="http://inside-r.org/r-doc/base/c"><span style="color: #003399; font-weight: bold">c</span></a><span style="color: #339933">,</span> vp = vplayout<span style="color: #009900">(</span><span style="color: #cc66cc">3</span><span style="color: #339933">,</span> <span style="color: #cc66cc">1</span><span style="color: #009900">)</span><span style="color: #009900">)</span><br /><span style="font-style: italic; color: #666666">#dev.off()</span></pre></div></div><br /><p><a title="Created by Pretty R at inside-R.org" href="http://www.inside-r.org/pretty-r">Created by Pretty R at inside-R.org</a></p> <div class="blogger-post-footer"><img width='1' height='1' src='https://blogger.googleusercontent.com/tracker/7630810606654250077-2875351857736250198?l=timelyportfolio.blogspot.com' alt='' /></div>klrhttp://www.blogger.com/profile/08783806801212705259noreply@blogger.com6tag:blogger.com,1999:blog-7630810606654250077.post-50648203448988618552011-09-15T13:19:00.001-07:002011-09-15T13:20:34.430-07:00<p>Sorry to all my faithful readers for my absence recently. I started a new job at a new firm, so my blogging has moved down the priority list but only temporarily. I am still committed to documenting my thoughts, especially finance and R thoughts as discussed in <a href="http://timelyportfolio.blogspot.com/2011/03/why-talk-my-book.html">Why Talk My Book?</a> . <p>So far, I have used R primarily for my own use without the intention of sharing with clients &lt;&gt; R stats finance geeks. However, R is so powerful that I would like to leverage it for more general communication. <p>Our shop uses Advent Axys, which I believe is still the industry standard despite its extremely poor and inflexible reporting capabilities. At one point in a previous life, I believed some of the inflexibility could be overcome through its replang scripting, and I endured a very painful journey documenting and experimenting <a href="http://www.axysreporting.com">http://www.axysreporting.com</a>. I now believe the best solution is to use Axys only to export its information to better, more capable reporting engines. <p>In this example, I amended the Axys 631 report to export performance to a .csv file. I'm concerned that sharing my amended report might violate the very aggressive IP attorneys at Advent. I will try to write from scratch at some point to share while still avoiding this ire.&nbsp; Please let me know if you have already done this to save me some time and effort.&nbsp; Click on the screenshot to get the .csv file from Google Docs. <p><a href="https://docs.google.com/leaf?id=0B2qp2r96khJPMzBmNjQzZTgtMzFjNy00MDkwLTg0Y2EtOTQyMWM3NTZiYjY3&amp;hl=en_US"><img style="background-image: none; border-right-width: 0px; padding-left: 0px; padding-right: 0px; display: inline; border-top-width: 0px; border-bottom-width: 0px; border-left-width: 0px; padding-top: 0px" title="image" border="0" alt="image" src="http://lh6.ggpht.com/-ydigNQE4y_E/TnJdyiklxaI/AAAAAAAB1Ds/hXwql1PPUlo/image%25255B4%25255D.png?imgmax=800" width="381" height="98"></a> <p>For now, I will share a sample performance file generated from my 631 exporter, and change the fine PerformanceAnalytics charts.PerformanceSummary report.&nbsp; In later posts I will add some ggplot2 charts.&nbsp; I think the chart is now good enough to share with clients, but unfortunately, my code is nowhere near as clean or robust as I would like.&nbsp; I combined all the code into one R script, and here is the result.&nbsp; I would love input and thoughts. <p>The original charts.PerformanceSummary with no modifications. <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/MSB6gBXNawAayB0QPktHeQ?feat=embedwebsite"><img src="https://lh3.googleusercontent.com/-s3rAeaz19bk/TnJb-7UluDI/AAAAAAAB1Dg/Ikr3D_pLVAg/s800/performance%252520summary.jpg" width="576" height="672"></a></td></tr> <tr> <td style="text-align: right; font-family: arial,sans-serif; font-size: 11px">From <a href="https://picasaweb.google.com/kentonlrussell/TimelyPortfolio02?authuser=0&amp;feat=embedwebsite">TimelyPortfolio</a></td></tr></tbody></table> <p>My new version <table style="width: auto"> <tbody> <tr> <td><a href="https://picasaweb.google.com/lh/photo/cf_1NZF43ckz8eud7ygWvw?feat=embedwebsite"><img src