<!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta charset="utf-8" /> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <meta name="generator" content="pandoc" /> <meta name="author" content="Lei Sun" /> <meta name="date" content="2017-03-29" /> <title>True Signal vs Correlated Null: Identifiability & Small Effects</title> <script src="site_libs/jquery-1.11.3/jquery.min.js"></script> <meta name="viewport" content="width=device-width, initial-scale=1" /> <link href="site_libs/bootstrap-3.3.5/css/cosmo.min.css" rel="stylesheet" /> <script src="site_libs/bootstrap-3.3.5/js/bootstrap.min.js"></script> <script src="site_libs/bootstrap-3.3.5/shim/html5shiv.min.js"></script> <script src="site_libs/bootstrap-3.3.5/shim/respond.min.js"></script> <script src="site_libs/jqueryui-1.11.4/jquery-ui.min.js"></script> <link href="site_libs/tocify-1.9.1/jquery.tocify.css" rel="stylesheet" /> <script src="site_libs/tocify-1.9.1/jquery.tocify.js"></script> <script src="site_libs/navigation-1.1/tabsets.js"></script> <link href="site_libs/highlightjs-1.1/textmate.css" rel="stylesheet" /> <script src="site_libs/highlightjs-1.1/highlight.js"></script> <link href="site_libs/font-awesome-4.5.0/css/font-awesome.min.css" rel="stylesheet" /> <style type="text/css">code{white-space: pre;}</style> <style type="text/css"> pre:not([class]) { background-color: white; } </style> <script type="text/javascript"> if (window.hljs && document.readyState && document.readyState === "complete") { window.setTimeout(function() { hljs.initHighlighting(); }, 0); } </script> <style type="text/css"> h1 { font-size: 34px; } h1.title { font-size: 38px; } h2 { font-size: 30px; } h3 { font-size: 24px; } h4 { font-size: 18px; } h5 { font-size: 16px; } h6 { font-size: 12px; } .table th:not([align]) { text-align: left; } </style> </head> <body> <style type = "text/css"> .main-container { max-width: 940px; margin-left: auto; margin-right: auto; } code { color: inherit; background-color: rgba(0, 0, 0, 0.04); } img { max-width:100%; height: auto; } .tabbed-pane { padding-top: 12px; } button.code-folding-btn:focus { outline: none; } </style> <style type="text/css"> /* padding for bootstrap navbar */ body { padding-top: 51px; padding-bottom: 40px; } /* offset scroll position for anchor links (for fixed navbar) */ .section h1 { padding-top: 56px; margin-top: -56px; } .section h2 { padding-top: 56px; margin-top: -56px; } .section h3 { padding-top: 56px; margin-top: -56px; } .section h4 { padding-top: 56px; margin-top: -56px; } .section h5 { padding-top: 56px; margin-top: -56px; } .section h6 { padding-top: 56px; margin-top: -56px; } </style> <script> // manage active state of menu based on current page $(document).ready(function () { // active menu anchor href = window.location.pathname href = href.substr(href.lastIndexOf('/') + 1) if (href === "") href = "index.html"; var menuAnchor = $('a[href="' + href + '"]'); // mark it active menuAnchor.parent().addClass('active'); // if it's got a parent navbar menu mark it active as well menuAnchor.closest('li.dropdown').addClass('active'); }); </script> <div class="container-fluid main-container"> <!-- tabsets --> <script> $(document).ready(function () { window.buildTabsets("TOC"); }); </script> <!-- code folding --> <script> $(document).ready(function () { // move toc-ignore selectors from section div to header $('div.section.toc-ignore') .removeClass('toc-ignore') .children('h1,h2,h3,h4,h5').addClass('toc-ignore'); // establish options var options = { selectors: "h1,h2,h3", theme: "bootstrap3", context: '.toc-content', hashGenerator: function (text) { return text.replace(/[.\\/?&!#<>]/g, '').replace(/\s/g, '_').toLowerCase(); }, ignoreSelector: ".toc-ignore", scrollTo: 0 }; options.showAndHide = true; options.smoothScroll = true; // tocify var toc = $("#TOC").tocify(options).data("toc-tocify"); }); </script> <style type="text/css"> #TOC { margin: 25px 0px 20px 0px; } @media (max-width: 768px) { #TOC { position: relative; width: 100%; } } .toc-content { padding-left: 30px; padding-right: 40px; } div.main-container { max-width: 1200px; } div.tocify { width: 20%; max-width: 260px; max-height: 85%; } @media (min-width: 768px) and (max-width: 991px) { div.tocify { width: 25%; } } @media (max-width: 767px) { div.tocify { width: 100%; max-width: none; } } .tocify ul, .tocify li { line-height: 20px; } .tocify-subheader .tocify-item { font-size: 0.90em; padding-left: 25px; text-indent: 0; } .tocify .list-group-item { border-radius: 0px; } </style> <!-- setup 3col/9col grid for toc_float and main content --> <div class="row-fluid"> <div class="col-xs-12 col-sm-4 col-md-3"> <div id="TOC" class="tocify"> </div> </div> <div class="toc-content col-xs-12 col-sm-8 col-md-9"> <div class="navbar navbar-default navbar-fixed-top" role="navigation"> <div class="container"> <div class="navbar-header"> <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar"> <span class="icon-bar"></span> <span class="icon-bar"></span> <span class="icon-bar"></span> </button> <a class="navbar-brand" href="index.html">truncash</a> </div> <div id="navbar" class="navbar-collapse collapse"> <ul class="nav navbar-nav"> <li> <a href="index.html">Home</a> </li> <li> <a href="about.html">About</a> </li> <li> <a href="license.html">License</a> </li> </ul> <ul class="nav navbar-nav navbar-right"> <li> <a href="https://github.com/LSun/truncash"> <span class="fa fa-github"></span> </a> </li> </ul> </div><!--/.nav-collapse --> </div><!--/.container --> </div><!--/.navbar --> <div class="fluid-row" id="header"> <h1 class="title toc-ignore">True Signal vs Correlated Null: Identifiability & Small Effects</h1> <h4 class="author"><em>Lei Sun</em></h4> <h4 class="date"><em>2017-03-29</em></h4> </div> <!-- The file analysis/chunks.R contains chunks that define default settings shared across the workflowr files. --> <!-- Update knitr chunk options --> <!-- Insert the date the file was last updated --> <p><strong>Last updated:</strong> 2017-05-30</p> <!-- Insert the code version (Git commit SHA1) if Git repository exists and R package git2r is installed --> <p><strong>Code version:</strong> 9f7dd01</p> <!-- Add your analysis here --> <div id="identifiablity-of-true-signals-from-correlated-noise" class="section level2"> <h2>Identifiablity of true signals from correlated noise</h2> <p><a href="gaussian_derivatives_2.html#examples">We’ve shown</a> that in many real data sets when we have correlated null <span class="math inline">\(z\)</span> scores, we can <a href="gaussian_derivatives.html#empirical_null">fit their empirical distribution with Gaussian and its derivatives</a>.</p> <p>But what if we have true signals instead of the global null? Theoretically, any distribution can be decomposed by Gaussian and its derivatives, also called <a href="https://en.wikipedia.org/wiki/Edgeworth_series">Edgeworth series or Edgeworth expansion</a>. We’ve shown that the Dirac delta function <span class="math inline">\(\delta_z\)</span> and the associated <span class="math inline">\(0\)</span>-<span class="math inline">\(1\)</span> step function <a href="gaussian_derivatives_4.html#extreme_case:_(rho_%7Bij%7D_equiv_1)">can be decomposed</a> by Gaussian derivatives. Essentially all distributions can be represented by (usually infinitely many) <span class="math inline">\(\delta_z\)</span>, and thus be decomposed by Gaussian and its derivatives. <strong>There is a rich literature on this topic, probably of further use to this project.</strong></p> <p>Now the more urgent problem is: can true signals also be fitted by Gaussian derivatives in a similar way as correlated null? Let normalized weights <span class="math inline">\(W_k^s = W_k\sqrt{k!}\)</span>. As <a href="gaussian_derivatives.html">shown previously</a>, under correlated null, the variance <span class="math inline">\(\text{var}(W_k^s) = \alpha_k = \bar{\rho_{ij}^k}\)</span>. Thus, under correlated null, the Gaussian derivative decomposition of the empirical distribution should have “reasonable” weights of similar decaying patterns.</p> <p>If it turns out Gaussian derivatives with limited orders (say, <span class="math inline">\(K \leq 10\)</span>) and reasonable normalized weights are only able to fit the empirical correlated null, but nothing else, then properly regularized Gaussian derivatives can be readily used to control the usually correlated <em>noise</em>, which are correlated null, and leave the <em>signal</em> to <code>ash</code>. But if true signals can also be fitted this way, the identifiability of true signals from correlated noise becomes an issue.</p> <p>Let’s start with the simplest case: <span class="math inline">\(z \sim N(0, \sqrt{2}^2)\)</span> independently. This data set can be seen as generated as follows.</p> <p><span class="math display">\[ \begin{array}{c} \beta_j \sim N(0, 1)\\ z_j \sim N(\beta_j, 1) \end{array} \]</span></p> <p>That is, a <span class="math inline">\(N(0, 1)\)</span> true signal is polluted by a <span class="math inline">\(N(0, 1)\)</span> noise.</p> </div> <div id="illustration" class="section level2"> <h2>Illustration</h2> <pre class="r"><code>n = 1e4 m = 5 set.seed(777) zmat = matrix(rnorm(n * m, 0, sd = sqrt(2)), nrow = m, byrow = TRUE)</code></pre> <pre class="r"><code>library(ashr) source("../code/ecdfz.R") res = list() for (i in 1:m) { z = zmat[i, ] p = (1 - pnorm(abs(z))) * 2 bh.fd = sum(p.adjust(p, method = "BH") <= 0.05) pihat0.ash = get_pi0(ash(z, 1, method = "fdr")) ecdfz.fit = ecdfz.optimal(z) res[[i]] = list(z = z, p = p, bh.fd = bh.fd, pihat0.ash = pihat0.ash, ecdfz.fit = ecdfz.fit) }</code></pre> <pre><code>Example 1 : Number of Discoveries: 246 ; pihat0 = 0.3245191 Log-likelihood with N(0, 2): -17704.62 Log-likelihood with Gaussian Derivatives: -17702.15 Log-likelihood ratio between true N(0, 2) and fitted Gaussian derivatives: -2.473037 Normalized weights: 1 : -0.0126888368547959 ; 2 : 0.717062378249889 ; 3 : -0.0184536200134752 ; 4 : 0.649465525394262 ; 5 : 0.00859163522314002 ; 6 : 0.521325079359314 ; 7 : 0.0334885164431775 ; 8 : 0.22636494735755 ;</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-1.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the left tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-2.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the right tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-3.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-4.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-5.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-6.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-7.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-8.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Example 2 : Number of Discoveries: 218 ; pihat0 = 0.3007316 Log-likelihood with N(0, 2): -17620.91 Log-likelihood with Gaussian Derivatives: -17618.13 Log-likelihood ratio between true N(0, 2) and fitted Gaussian derivatives: -2.787631 Normalized weights: 1 : 0.0102680011779709 ; 2 : 0.696012169853609 ; 3 : 0.0113000171720435 ; 4 : 0.544236663386519 ; 5 : -0.0208432030918437 ; 6 : 0.359654087688657 ; 7 : 0.00449356234470338 ; 8 : 0.129368209367989 ;</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-9.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the left tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-10.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the right tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-11.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-12.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-13.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-14.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-15.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-16.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Example 3 : Number of Discoveries: 201 ; pihat0 = 0.3524008 Log-likelihood with N(0, 2): -17627.66 Log-likelihood with Gaussian Derivatives: -17623.26 Log-likelihood ratio between true N(0, 2) and fitted Gaussian derivatives: -4.397359 Normalized weights: 1 : 0.000611199281683122 ; 2 : 0.697833563596919 ; 3 : -9.24232505276873e-05 ; 4 : 0.593310577011007 ; 5 : 0.0690423192366928 ; 6 : 0.402719962212205 ; 7 : 0.0821756084741036 ; 8 : 0.137136244590824 ;</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-17.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the left tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-18.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the right tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-19.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-20.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-21.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-22.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-23.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-24.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Example 4 : Number of Discoveries: 134 ; pihat0 = 0.3039997 Log-likelihood with N(0, 2): -17572.28 Log-likelihood with Gaussian Derivatives: -17589.35 Log-likelihood ratio between true N(0, 2) and fitted Gaussian derivatives: 17.07424 Normalized weights: 1 : -0.00303021567753385 ; 2 : 0.667140676046508 ; 3 : -0.00744442518950379 ; 4 : 0.4335954662891 ; 5 : 0.00652056989516479 ; 6 : 0.163579551221406 ; 7 : 0.0434395776822699 ;</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-25.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the left tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-26.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the right tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-27.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-28.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-29.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-30.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-31.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-32.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Example 5 : Number of Discoveries: 201 ; pihat0 = 0.3864133 Log-likelihood with N(0, 2): -17602.8 Log-likelihood with Gaussian Derivatives: -17607.36 Log-likelihood ratio between true N(0, 2) and fitted Gaussian derivatives: 4.565327 Normalized weights: 1 : -0.0149505230188178 ; 2 : 0.681006373173563 ; 3 : -0.029408092099831 ; 4 : 0.526597120212115 ; 5 : -0.0649823448928799 ; 6 : 0.248323484516014 ; 7 : -0.077154633635199 ;</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-33.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the left tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-34.png" width="672" style="display: block; margin: auto;" /></p> <pre><code>Zoom in to the right tail:</code></pre> <p><img src="figure/alternative.rmd/unnamed-chunk-4-35.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-36.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-37.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-38.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-39.png" width="672" style="display: block; margin: auto;" /><img src="figure/alternative.rmd/unnamed-chunk-4-40.png" width="672" style="display: block; margin: auto;" /></p> </div> <div id="session-information" class="section level2"> <h2>Session information</h2> <!-- Insert the session information into the document --> <pre class="r"><code>sessionInfo()</code></pre> <pre><code>R version 3.3.3 (2017-03-06) Platform: x86_64-apple-darwin13.4.0 (64-bit) Running under: macOS Sierra 10.12.5 locale: [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] cvxr_0.0.0.9009 EQL_1.0-0 ttutils_1.0-1 ashr_2.1-13 loaded via a namespace (and not attached): [1] Rcpp_0.12.10 knitr_1.16 magrittr_1.5 [4] REBayes_0.85 MASS_7.3-47 doParallel_1.0.10 [7] pscl_1.4.9 SQUAREM_2016.10-1 lattice_0.20-35 [10] R6_2.2.1 foreach_1.4.3 stringr_1.2.0 [13] tools_3.3.3 parallel_3.3.3 grid_3.3.3 [16] git2r_0.18.0 htmltools_0.3.6 iterators_1.0.8 [19] assertthat_0.2.0 yaml_2.1.14 rprojroot_1.2 [22] digest_0.6.12 Matrix_1.2-10 codetools_0.2-15 [25] evaluate_0.10 rmarkdown_1.5 stringi_1.1.5 [28] Rmosek_7.1.2 backports_1.0.5 truncnorm_1.0-7 </code></pre> </div> <hr> <p> This <a href="http://rmarkdown.rstudio.com">R Markdown</a> site was created with <a href="https://github.com/jdblischak/workflowr">workflowr</a> </p> <hr> <!-- To enable disqus, uncomment the section below and provide your disqus_shortname --> <!-- disqus <div id="disqus_thread"></div> <script type="text/javascript"> /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */ var disqus_shortname = 'rmarkdown'; // required: replace example with your forum shortname /* * * DON'T EDIT BELOW THIS LINE * * */ (function() { var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true; dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js'; (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq); })(); </script> <noscript>Please enable JavaScript to view the <a href="http://disqus.com/?ref_noscript">comments powered by Disqus.</a></noscript> <a href="http://disqus.com" class="dsq-brlink">comments powered by <span class="logo-disqus">Disqus</span></a> --> </div> </div> </div> <script> // add bootstrap table styles to pandoc tables function bootstrapStylePandocTables() { $('tr.header').parent('thead').parent('table').addClass('table table-condensed'); } $(document).ready(function () { bootstrapStylePandocTables(); }); </script> <!-- dynamically load mathjax for compatibility with self-contained --> <script> (function () { var script = document.createElement("script"); script.type = "text/javascript"; script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"; document.getElementsByTagName("head")[0].appendChild(script); })(); </script> </body> </html>