<!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="2017-04-16" /> <title>Diagnostic Plots for ASH (and Empirical Bayes)</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">Diagnostic Plots for ASH (and Empirical Bayes)</h1> <h4 class="author"><em>Lei Sun</em></h4> <h4 class="date"><em>2017-04-16</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> 2017-04-18</p> <!-- Insert the code version (Git commit SHA1) if Git repository exists and R package git2r is installed --> <p><strong>Code version:</strong> 020da62</p> <!-- Add your analysis here --> <div id="ash-and-empirical-bayes" class="section level2"> <h2><code>ASH</code> and empirical Bayes</h2> <p>Under <a href="https://academic.oup.com/biostatistics/article/18/2/275/2557030/False-discovery-rates-a-new-deal">ASH setting</a>, the observations <span class="math inline">\(\left\{\left(\hat\beta_j, \hat s_j\right)\right\}\)</span> come from a likelihood <span class="math inline">\(p\left(\hat\beta_j\mid\beta_j,\hat s_j\right)\)</span> which could be <span class="math inline">\(N\left(\beta_j, \hat s_j^2\right)\)</span> or <a href="t-likelihood.html">a noncentral-<span class="math inline">\(t\)</span></a>. Recently, a likelihood of <a href="ash_gd.html">Gaussian derivative composition</a> has also been proposed.</p> <p>Further, as essentially all empirical Bayes approaches go, a hierarchical model assumes that all <span class="math inline">\(\left\{\beta_j\right\}\)</span> come exchangeably from a prior of effect size distribution <span class="math inline">\(g\)</span>. Therefore, the likelihood of <span class="math inline">\(\hat\beta_j | \hat s_j\)</span> is given by</p> <p><span class="math display">\[ \displaystyle f\left(\hat\beta_j\mid\hat s_j\right) = \int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g(\beta_j)d\beta_j\ \ . \]</span></p> <p>Then <span class="math inline">\(\hat g\)</span> is estimated by</p> <p><span class="math display">\[ \displaystyle \hat g = \arg\max_g \prod_j f\left(\hat\beta_j\mid\hat s_j\right) = \arg\max_g \prod_j\int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g(\beta_j)d\beta_j \ \ . \]</span></p> <p>Under ASH framework in particular, the unimodal <span class="math inline">\(g = \sum_k\pi_kg_k\)</span> is a mixture of normal or a mixture of uniform, and</p> <p><span class="math display">\[ \begin{array}{rcl} \displaystyle f\left(\hat\beta_j\mid\hat s_j\right) &=& \displaystyle\int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g(\beta_j)d\beta_j \\ &=& \displaystyle\int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) \sum_k\pi_kg_k(\beta_j)d\beta_j\\ &=& \displaystyle\sum_k\pi_k\int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j\\ &:=&\displaystyle\sum_k\pi_kf_{jk}\ \ . \end{array} \]</span></p> </div> <div id="goodness-of-fit-for-empirical-bayes" class="section level2"> <h2>Goodness of fit for empirical Bayes</h2> <p>In empirical Bayes, if <span class="math inline">\(g\left(\beta\right)\)</span> is the true effect size distribution, and equally important, if <span class="math inline">\(p\left(\hat\beta_j\mid\beta_j, \hat s_j\right)\)</span> is the true observation likelihood, <span class="math inline">\(f\left(\hat\beta_j\mid\hat s_j\right)\)</span> should be the true distribution of <span class="math inline">\(\hat\beta_j\)</span> given <span class="math inline">\(\hat s_j\)</span>. Thus <span class="math inline">\(\hat\beta_j\)</span> can be seen as independent samples from their perspective distribution <span class="math inline">\(f\left(\hat\beta_j\mid\hat s_j\right)\)</span>, given <span class="math inline">\(\hat s_j\)</span>. Or to write it more formally,</p> <p><span class="math display">\[ \hat\beta_j | \hat s_j \sim f_{\hat\beta_j|\hat s_j}(\cdot|\hat s_j) \ \ . \]</span> Note that <a href="https://en.wikipedia.org/wiki/Probability_integral_transform">the cumulative distribution function of a continuous random variable should itself be a random variable following <span class="math inline">\(\text{Unif }[0, 1]\)</span></a>. Therefore, the cumulative distribution function at <span class="math inline">\(\hat\beta_j\)</span>,</p> <p><span class="math display">\[ \displaystyle F_j := F_{\hat\beta_j|\hat s_j} \left(\hat\beta_j|\hat s_j\right) = \int_{-\infty}^{\hat\beta_j} f_{\hat\beta_j|\hat s_j}\left(t|\hat s_j\right)dt \ , \]</span> should be a random sample from <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span>.</p> <p>In other words, in empirical Bayes models, <span class="math inline">\(\left\{F_{\hat\beta_1|\hat s_1}(\hat\beta_1|\hat s_1), \ldots, F_{\hat\beta_n|\hat s_n}(\hat\beta_n|\hat s_n)\right\}\)</span> should behave like <span class="math inline">\(n\)</span> independent samples from <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> if the hierarchical model assumption holds.</p> <p>In practice, a <span class="math inline">\(\hat g\)</span> is then estimated by maximizing the joint likelihood <span class="math inline">\(\displaystyle\prod_j f_{\hat\beta_j|\hat s_j}\left(\hat\beta_j\mid\hat s_j\right) = \prod_j \int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g(\beta_j)d\beta_j\)</span>. <span class="math inline">\(\displaystyle\hat F_j := \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right) = \int_{-\infty}^{\hat\beta_j}\hat f_{\hat\beta_j|\hat s_j}\left(t|\hat s_j\right)dt = \int_{-\infty}^{\hat\beta_j}\int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right)\hat g(\beta_j)d\beta_jdt\)</span> can thus be calculated.</p> <p>If all of the following there statments hold,</p> <ol style="list-style-type: decimal"> <li>The hierarchical model assumption is sufficiently valid.</li> <li>The assumptions inposed on <span class="math inline">\(g\)</span> are sufficiently accurate.</li> <li>The estimate of <span class="math inline">\(\hat g\)</span> is sufficiently satisfactory.</li> </ol> <p>then <strong><span class="math inline">\(\left\{\hat F_{\hat\beta_1|\hat s_1}(\hat\beta_1|\hat s_1), \ldots, \hat F_{\hat\beta_n|\hat s_n}(\hat\beta_n|\hat s_n)\right\}\)</span> should look like <span class="math inline">\(n\)</span> independent random samples from <span class="math inline">\(\text{Unif }[0, 1]\)</span></strong>, and their behavior can be used to gauge the goodness of fit of an empirical Bayes model.</p> </div> <div id="goodness-of-fit-for-ash" class="section level2"> <h2>Goodness of fit for <code>ASH</code></h2> <p>In ASH setting,</p> <p><span class="math display">\[ \begin{array}{rcl} \hat F_j := \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right) &=&\displaystyle \int_{-\infty}^{\hat\beta_j} \hat f_{\hat\beta_j|\hat s_j}\left(t|\hat s_j\right)dt\\ &=&\displaystyle \int_{-\infty}^{\hat\beta_j} \sum_k\hat\pi_k \int p\left(t\mid\beta_j,\hat s_j\right) \hat g_k(\beta_j)d\beta_j dt\\ &=&\displaystyle\sum_k\hat\pi_k \int_{-\infty}^{\hat\beta_j} \int p\left(t\mid\beta_j,\hat s_j\right) \hat g_k(\beta_j)d\beta_j dt\\ &:=& \displaystyle\sum_k\hat\pi_k \hat F_{jk}\ \ . \end{array} \]</span> A diagnostic procedure of <code>ASH</code> can be produced in the following steps.</p> <ol style="list-style-type: decimal"> <li>Fit <code>ASH</code>, get <span class="math inline">\(\hat g_k\)</span>, <span class="math inline">\(\hat \pi_k\)</span>.</li> <li>Compute <span class="math inline">\(\displaystyle\hat F_{jk} = \int_{-\infty}^{\hat\beta_j}\int p\left(t\mid\beta_j,\hat s_j\right)\hat g_k(\beta_j)d\beta_j dt\)</span>. Note the computation doesn’t have to be expensive, because as detailed below, usually intermediate results in <code>ASH</code> can be recycled.</li> <li>Compute <span class="math inline">\(\hat F_j = \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right) = \displaystyle\sum_k\hat\pi_k\hat F_{jk}\)</span>.</li> <li>Compare the calculated <span class="math inline">\(\left\{\hat F_1 = \hat F_{\hat\beta_1|\hat s_1}(\hat\beta_1|\hat s_1), \ldots, \hat F_n = \hat F_{\hat\beta_n|\hat s_n}(\hat\beta_n|\hat s_n)\right\}\)</span> with <span class="math inline">\(n\)</span> random samples from <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> by the histogram, Q-Q plot, statistical tests, etc.</li> </ol> </div> <div id="ash-normal-likelihood-normal-mixture-prior" class="section level2"> <h2><code>ASH</code>: normal likelihood, normal mixture prior</h2> <p><span class="math inline">\(g = \sum_k\pi_kg_k\)</span>, where <span class="math inline">\(g_k\)</span> is <span class="math inline">\(N\left(\mu_k, \sigma_k^2\right)\)</span>. Let <span class="math inline">\(\varphi_{\mu, \sigma^2}\left(\cdot\right)\)</span> be the probability density function (pdf) of <span class="math inline">\(N\left(\mu, \sigma^2\right)\)</span>.</p> <p><span class="math display">\[ \begin{array}{r} \displaystyle \begin{array}{r} p = \varphi_{\beta_j, \hat s_j^2}\\ g_k = \varphi_{\mu_k, \sigma_k^2} \end{array} \Rightarrow \int p\left(t\mid\beta_j,\hat s_j\right) g_k\left(\beta_j\right)d\beta_j = \varphi_{\mu_k, \sigma_k^2 + \hat s_j^2}(t)\\ \displaystyle \Rightarrow \hat F_{jk} = \int_{-\infty}^{\hat\beta_j} \int p\left(t\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j dt = \int_{-\infty}^{\hat\beta_j} \varphi_{\mu_k, \sigma_k^2 + \hat s_j^2}(t) dt =\Phi\left(\frac{\hat\beta_j - \mu_k}{\sqrt{\sigma_k^2 + \hat s_j^2}}\right)\\ \displaystyle \Rightarrow \hat F_j = \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right) =\sum_k\hat\pi_k\hat F_{jk} =\sum_k\hat\pi_k \Phi\left(\frac{\hat\beta_j - \mu_k}{\sqrt{\sigma_k^2 + \hat s_j^2}}\right). \end{array} \]</span> Note that in this case, when fitting <code>ASH</code>,</p> <p><span class="math display">\[ f_{jk} = \int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j = \varphi_{\mu_k, \sigma_k^2 + \hat s_j^2}\left(\hat\beta_j\right) = \frac{1}{\sqrt{\sigma_k^2 + \hat s_j^2}}\varphi\left(\frac{\hat\beta_j - \mu_k}{\sqrt{\sigma_k^2 + \hat s_j^2}}\right). \]</span> Therefore, the matrix of <span class="math inline">\(\left[\frac{\hat\beta_j - \mu_k}{\sqrt{\sigma_k^2 + \hat s_j^2}}\right]_{jk}\)</span> should be created when fitting <code>ASH</code>. We can re-use it when calculating <span class="math inline">\(\hat F_{jk}\)</span> and <span class="math inline">\(\hat F_j = \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right)\)</span>.</p> <div id="illustrative-example" class="section level3"> <h3>Illustrative Example</h3> <p><span class="math inline">\(n = 1000\)</span> observations <span class="math inline">\(\left\{\left(\hat\beta_1, \hat s_1\right), \ldots, \left(\hat\beta_n, \hat s_n\right)\right\}\)</span> are generated as follows</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \\ \beta_j &\sim& 0.5\delta_0 + 0.5N(0, 1)\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1 &\sim& N\left(\beta_j, \hat s_j^2 \equiv1\right)\ . \end{array} \]</span></p> <pre class="r"><code>set.seed(100) n = 1000 sebetahat = 1 beta = c(rnorm(n * 0.5, 0, 1), rep(0, n * 0.5)) betahat = rnorm(n, beta, sebetahat)</code></pre> <p>First fit <code>ASH</code> to get <span class="math inline">\(\hat\pi_k\)</span> and <span class="math inline">\(\hat g_k = N\left(\hat\mu_k\equiv0, \hat\sigma_k^2\right)\)</span>. Here we are using <code>pointmass = TRUE</code> and <code>prior = "uniform"</code> to impose a point mass but not penalize the non-point mass part, because the emphasis right now is to get an accurate estimate <span class="math inline">\(\hat g\)</span>.</p> <pre class="r"><code>fit.ash.n.n = ash.workhorse(betahat, sebetahat, mixcompdist = "normal", pointmass = TRUE, prior = "uniform") data = fit.ash.n.n$data ghat = get_fitted_g(fit.ash.n.n)</code></pre> <p>Then form the <span class="math inline">\(n \times K\)</span> matrix of <span class="math inline">\(\hat F_{jk}\)</span> and the <span class="math inline">\(n\)</span>-vector <span class="math inline">\(\hat F_j\)</span>.</p> <pre class="r"><code>Fjkhat = pnorm(outer(data$x, ghat$mean, "-") / sqrt(outer((data$s)^2, ghat$sd^2, "+"))) Fhat = Fjkhat %*% ghat$pi</code></pre> <p>For a fair comparison, oracle <span class="math inline">\(F_{jk}\)</span> and <span class="math inline">\(F_j\)</span> under true <span class="math inline">\(g\)</span> are also calculated.</p> <pre class="r"><code>gtrue = normalmix(pi = c(0.5, 0.5), mean = c(0, 0), sd = c(0, 1)) Fjktrue = pnorm(outer(data$x, gtrue$mean, "-") / sqrt(outer((data$s)^2, gtrue$sd^2, "+"))) Ftrue = Fjktrue %*% gtrue$pi</code></pre> <p>Plot the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> and ordered <span class="math inline">\(\left\{\hat F_{\left(j\right)}\right\} = \left\{\hat F_{(1)}, \ldots, \hat F_{(n)}\right\}\)</span>. Under goodness of fit, the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> should look like <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> and <span class="math inline">\(\left\{\hat F_{(j)}\right\}\)</span> should look like a straight line from <span class="math inline">\(0\)</span> to <span class="math inline">\(1\)</span>. Oracle <span class="math inline">\(\left\{F_j\right\}\)</span> and <span class="math inline">\(\left\{F_{\left(j\right)}\right\}\)</span> under true <span class="math inline">\(g\)</span> are also plotted in the same way for comparison.</p> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-5-1.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-5-2.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-5-3.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-5-4.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-5-5.png" width="672" style="display: block; margin: auto;" /></p> </div> </div> <div id="ash-normal-likelihood-uniform-mixture-prior" class="section level2"> <h2><code>ASH</code>: normal likelihood, uniform mixture prior</h2> <p><span class="math inline">\(g = \sum_k\pi_kg_k\)</span>, where <span class="math inline">\(g_k\)</span> is <span class="math inline">\(\text{Unif}\left[a_k, b_k\right]\)</span>. Let <span class="math inline">\(U_{a, b}\)</span> be the probability density function (pdf) of <span class="math inline">\(\text{Unif}\left[a, b\right]\)</span>. An important fact regarding the integral of the cumulative distribution function of the standard normal <span class="math inline">\(\Phi\)</span> is as follows,</p> <p><span class="math display">\[ \int_{-\infty}^c\Phi(t)dt = c\Phi(c) +\varphi(c) \]</span></p> <p>Therefore,</p> <p><span class="math display">\[ \begin{array}{r} \displaystyle \begin{array}{r} p = \varphi_{\beta_j, \hat s_j^2}\\ g_k = U_{a_k, b_k} \end{array} \Rightarrow \displaystyle \int p\left(t\mid\beta_j,\hat s_j\right) g_k\left(\beta_j\right)d\beta_j = \frac{\Phi\left(\frac{t - a_k}{\hat s_j}\right) - \Phi\left(\frac{t - b_k}{\hat s_j}\right)}{b_k - a_k} \\ \displaystyle \Rightarrow \hat F_{jk} = \int_{-\infty}^{\hat\beta_j} \int p\left(t\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j dt = \frac{1}{b_k - a_k}\left( \int_{-\infty}^{\hat\beta_j} \Phi\left(\frac{t - a_k}{\hat s_j}\right) dt - \int_{-\infty}^{\hat\beta_j} \Phi\left(\frac{t - b_k}{\hat s_j}\right) dt \right)\\ = \frac{\hat s_j}{b_k - a_k} \left( \left( \frac{\hat\beta_j - a_k}{\hat s_j}\Phi\left(\frac{\hat\beta_j - a_k}{\hat s_j}\right) +\varphi\left(\frac{\hat\beta_j - a_k}{\hat s_j}\right) \right) - \left( \frac{\hat\beta_j - b_k}{\hat s_j}\Phi\left(\frac{\hat\beta_j - b_k}{\hat s_j}\right) +\varphi\left(\frac{\hat\beta_j - b_k}{\hat s_j}\right) \right) \right) \\ \Rightarrow \hat F_j = \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right) = \sum_k\hat\pi_k \hat F_{jk}\\ =\sum_k\hat\pi_k \left( \frac{\hat s_j}{b_k - a_k} \left( \left( \frac{\hat\beta_j - a_k}{\hat s_j}\Phi\left(\frac{\hat\beta_j - a_k}{\hat s_j}\right) +\varphi\left(\frac{\hat\beta_j - a_k}{\hat s_j}\right) \right) - \left( \frac{\hat\beta_j - b_k}{\hat s_j}\Phi\left(\frac{\hat\beta_j - b_k}{\hat s_j}\right) +\varphi\left(\frac{\hat\beta_j - b_k}{\hat s_j}\right) \right) \right) \right). \end{array} \]</span> In particular, if <span class="math inline">\(a_k = b_k = \mu_k\)</span>, or in other words, <span class="math inline">\(g_k = \delta_{\mu_k}\)</span>,</p> <p><span class="math display">\[ \begin{array}{rcl} \displaystyle \hat F_{jk} &=& \displaystyle \int_{-\infty}^{\hat\beta_j} \int p\left(t\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j dt \\ &=& \displaystyle \int_{-\infty}^{\hat\beta_j} \int \varphi_{\beta_j, \hat s_j^2}(t) \delta_{\mu_k}\left(\beta_j\right)d\beta_jdt \\ &=& \displaystyle \int \Phi\left(\frac{\hat\beta_j - \beta_j}{\hat s_j}\right) \delta_{\mu_k}\left(\beta_j\right) d\beta_j \\ &=& \displaystyle \Phi\left(\frac{\hat\beta_j - \mu_k}{\hat s_j}\right). \end{array} \]</span></p> <p>Note that, similar to the previous case, when fitting <code>ASH</code>,</p> <p><span class="math display">\[ f_{jk} = \int p\left(\hat\beta_j\mid\beta_j,\hat s_j\right) g_k(\beta_j)d\beta_j = \begin{cases} \displaystyle\frac{\Phi\left(\frac{\hat\beta_j - a_k}{\hat s_j}\right) - \Phi\left(\frac{\hat\beta_j - b_k}{\hat s_j}\right)}{b_k - a_k} & a_k < b_k\\ \displaystyle\frac{1}{\hat s_j}\varphi\left(\frac{\hat\beta_j - \mu_k}{\hat s_j}\right) & a_k = b_k = \mu_k \end{cases}. \]</span></p> <p>Therefore, both matrices of <span class="math inline">\(\left[\frac{\hat\beta_j - a_k}{\hat s_j}\right]_{jk}\)</span> and <span class="math inline">\(\left[\frac{\hat\beta_j - b_k}{\hat s_j}\right]_{jk}\)</span> should be created when fitting <code>ASH</code>. We can re-use them when calculating <span class="math inline">\(\hat F_{jk}\)</span> and <span class="math inline">\(\hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right)\)</span>.</p> <div id="illustrative-example-1" class="section level3"> <h3>Illustrative Example</h3> <p><span class="math inline">\(n = 1000\)</span> observations <span class="math inline">\(\left\{\left(\hat\beta_1, \hat s_1\right), \ldots, \left(\hat\beta_n, \hat s_n\right)\right\}\)</span> are generated as follows</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \\ \beta_j &\sim& 0.5\delta_0 + 0.5\text{Unif}\left[-1, 1\right]\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1 &\sim& N\left(\beta_j, \hat s_j^2 \equiv1\right)\ . \end{array} \]</span></p> <pre class="r"><code>set.seed(100) n = 1000 sebetahat = 1 beta = c(runif(n * 0.5, -1, 1), rep(0, n * 0.5)) betahat = rnorm(n, beta, sebetahat)</code></pre> <p>First fit <code>ASH</code> to get <span class="math inline">\(\hat\pi_k\)</span> and <span class="math inline">\(\hat g_k = \text{Unif}\left[\hat a_k, \hat b_k\right]\)</span>. Here we are using <code>pointmass = TRUE</code> and <code>prior = "uniform"</code> to impose a point mass but not penalize the non-point mass part, because the emphasis right now is to get an accurate estimate <span class="math inline">\(\hat g\)</span>.</p> <pre class="r"><code>fit.ash.n.u = ash.workhorse(betahat, sebetahat, mixcompdist = "uniform", pointmass = TRUE, prior = "uniform") data = fit.ash.n.u$data ghat = get_fitted_g(fit.ash.n.u)</code></pre> <p>Then form the <span class="math inline">\(n \times K\)</span> matrix of <span class="math inline">\(\hat F_{jk}\)</span> and the <span class="math inline">\(n\)</span>-vector <span class="math inline">\(\hat F_j\)</span>.</p> <pre class="r"><code>a_mat = outer(data$x, ghat$a, "-") / data$s b_mat = outer(data$x, ghat$b, "-") / data$s Fjkhat = ((a_mat * pnorm(a_mat) + dnorm(a_mat)) - (b_mat * pnorm(b_mat) + dnorm(b_mat))) / (a_mat - b_mat) Fjkhat[a_mat == b_mat] = pnorm(a_mat[a_mat == b_mat]) Fhat = Fjkhat %*% ghat$pi</code></pre> <p>For a fair comparison, oracle <span class="math inline">\(F_{jk}\)</span> and <span class="math inline">\(F_j\)</span> under true <span class="math inline">\(g\)</span> are also calculated.</p> <pre class="r"><code>gtrue = unimix(pi = c(0.5, 0.5), a = c(0, -1), b = c(0, 1)) a_mat = outer(data$x, gtrue$a, "-") / data$s b_mat = outer(data$x, gtrue$b, "-") / data$s Fjktrue = ((a_mat * pnorm(a_mat) + dnorm(a_mat)) - (b_mat * pnorm(b_mat) + dnorm(b_mat))) / (a_mat - b_mat) Fjktrue[a_mat == b_mat] = pnorm(a_mat[a_mat == b_mat]) Ftrue = Fjktrue %*% gtrue$pi</code></pre> <p>Plot the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> and ordered <span class="math inline">\(\left\{\hat F_{\left(j\right)}\right\} = \left\{\hat F_{(1)}, \ldots, \hat F_{(n)}\right\}\)</span>. Under goodness of fit, the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> should look like <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> and <span class="math inline">\(\left\{\hat F_{(j)}\right\}\)</span> should look like a straight line from <span class="math inline">\(0\)</span> to <span class="math inline">\(1\)</span>. Oracle <span class="math inline">\(\left\{F_j\right\}\)</span> and <span class="math inline">\(\left\{F_{\left(j\right)}\right\}\)</span> under true <span class="math inline">\(g\)</span> are also plotted in the same way for comparison.</p> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-10-1.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-10-2.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-10-3.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-10-4.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-10-5.png" width="672" style="display: block; margin: auto;" /></p> </div> </div> <div id="ash-t-likelihood-uniform-mixture-prior" class="section level2"> <h2><code>ASH</code>: <span class="math inline">\(t\)</span> likelihood, uniform mixture prior</h2> <p>In this case, <span class="math inline">\(\hat F_j = \hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j|\hat s_j\right)\)</span> involves calculting an integral of the cumulative distribution function (CDF) of Student’s <span class="math inline">\(t\)</span> distribution, which does not have an analytical expression.</p> <p>Let <span class="math inline">\(t_{\nu}\)</span> and <span class="math inline">\(T_{\nu}\)</span> denote the pdf and cdf of Student’s <span class="math inline">\(t\)</span> distribution with <span class="math inline">\(\nu\)</span> degrees of freedom. <a href="t-likelihood.html">Current implementation when dealing with <span class="math inline">\(t\)</span> likelihood</a> assumes that</p> <p><span class="math display">\[ \begin{array}{rl} \hat\beta_j | \beta_j, \hat s_j = \beta_j + \hat s_j t_j\\ t_j|\hat\nu_j \sim t_{\hat\nu_j}\\ \beta_j \sim g = \sum_k\pi_kg_k = \sum_k\pi_k\text{Unif}\left[a_k, b_k\right] & . \end{array} \]</span> Therefore, the likelihood of <span class="math inline">\(\hat\beta_j = t\)</span> given <span class="math inline">\(\beta_j, \hat s_j, \hat\nu_j\)</span> should be</p> <p><span class="math display">\[ p\left(\hat\beta_j = t | \beta_j, \hat s_j, \hat\nu_j\right) = \frac1{\hat s_j}t_{\hat\nu_j}\left(\frac{t - \beta_j}{\hat s_j}\right), \]</span></p> <p>which gives</p> <p><span class="math display">\[ \begin{array}{rcl} \hat F_{jk} &=& \displaystyle \int_{-\infty}^{\hat\beta_j} \int p\left(t\mid\beta_j,\hat s_j, \hat\nu_j\right) g_k\left(\beta_j\right)d\beta_j dt\\ &=& \displaystyle \int \left(\int_{-\infty}^{\hat\beta_j} \frac1{\hat s_j}t_{\hat\nu_j}\left(\frac{t - \beta_j}{\hat s_j}\right)dt\right) g_k\left(\beta_j\right)d\beta_j\\ &=& \displaystyle \int T_{\hat\nu_j}\left(\frac{\hat\beta_j - \beta_j}{\hat s_j}\right) g_k\left(\beta_j\right)d\beta_j\\ &=&\begin{cases} \displaystyle \frac{\hat s_j}{b_k - a_k} \int_{\frac{\hat\beta_j - b_k}{\hat s_j}}^{\frac{\hat\beta_j - a_k}{\hat s_j}} T_{\hat\nu_j}(t)dt & a_k < b_k\\ T_{\hat\nu_j}\left(\frac{\hat\beta_j - \mu_k}{\hat s_j}\right) & a_k = b_k = \mu_k \end{cases}. \end{array} \]</span> Thus, in order to evaluate <span class="math inline">\(\hat F_{jk}\)</span>, we need to evaluate as many as <span class="math inline">\(n \times K\)</span> integrals of the CDF of Student’s <span class="math inline">\(t\)</span> distribution. The operation is not difficult to code but might be expensive to compute.</p> <div id="illustrative-example-2" class="section level3"> <h3>Illustrative Example</h3> <p><span class="math inline">\(n = 1000\)</span> observations <span class="math inline">\(\left\{\left(\hat\beta_1, \hat s_1\right), \ldots, \left(\hat\beta_n, \hat s_n\right)\right\}\)</span> are generated as follows</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \\ \hat \nu_j &\equiv& 5 \\ t_j|\hat\nu_j \equiv5 &\sim& t_{\hat\nu_j\equiv5} \\ \beta_j &\sim& 0.5\delta_0 + 0.5\text{Unif}\left[-1, 1\right]\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1, t_j &=& \beta_j + \hat s_jt_j \ . \end{array} \]</span></p> <pre class="r"><code>set.seed(100) n = 1000 sebetahat = 1 nuhat = 5 t = rt(n, df = nuhat) beta = c(runif(n * 0.5, -1, 1), rep(0, n * 0.5)) betahat = beta + sebetahat * t</code></pre> <p>First fit <code>ASH</code> to get <span class="math inline">\(\hat\pi_k\)</span> and <span class="math inline">\(\hat g_k = \text{Unif}\left[\hat a_k, \hat b_k\right]\)</span>. Here we are using <code>pointmass = TRUE</code> and <code>prior = "uniform"</code> to impose a point mass but not penalize the non-point mass part, because the emphasis right now is to get an accurate estimate <span class="math inline">\(\hat g\)</span>.</p> <pre class="r"><code>fit.ash.t.u = ash.workhorse(betahat, sebetahat, mixcompdist = "uniform", pointmass = TRUE, prior = "uniform", df = nuhat) data = fit.ash.t.u$data ghat = get_fitted_g(fit.ash.t.u)</code></pre> <p>Then form the <span class="math inline">\(n \times K\)</span> matrix of <span class="math inline">\(\hat F_{jk}\)</span> and the <span class="math inline">\(n\)</span>-vector <span class="math inline">\(\hat F_j\)</span>. As seen right now a <code>for</code> loop is used to calculate <span class="math inline">\(n \times K\)</span> integration with <span class="math inline">\(n \times K\)</span> different lower and upper integral bounds. <strong>There should be a better way to do this.</strong></p> <pre class="r"><code>a_mat = outer(data$x, ghat$a, "-") / data$s b_mat = outer(data$x, ghat$b, "-") / data$s Fjkhat = matrix(nrow = nrow(a_mat), ncol = ncol(a_mat)) for (i in 1:nrow(a_mat)) { for (j in 1:ncol(a_mat)) { ind = (a_mat[i, j] == b_mat[i, j]) if (!ind) { Fjkhat[i, j] = (integrate(pt, b_mat[i, j], a_mat[i, j], df = fit.ash.t.u$result$df[i])$value) / (a_mat[i, j] - b_mat[i, j]) } else { Fjkhat[i, j] = pt(a_mat[i, j], df = fit.ash.t.u$result$df[i]) } } } Fhat = Fjkhat %*% ghat$pi</code></pre> <p>For a fair comparison, oracle <span class="math inline">\(F_{jk}\)</span> and <span class="math inline">\(F_j\)</span> under true <span class="math inline">\(g\)</span> are also calculated.</p> <pre class="r"><code>gtrue = unimix(pi = c(0.5, 0.5), a = c(0, -1), b = c(0, 1)) a_mat = outer(data$x, gtrue$a, "-") / data$s b_mat = outer(data$x, gtrue$b, "-") / data$s Fjktrue = matrix(nrow = nrow(a_mat), ncol = ncol(a_mat)) for (i in 1:nrow(a_mat)) { for (j in 1:ncol(a_mat)) { ind = (a_mat[i, j] == b_mat[i, j]) if (!ind) { Fjktrue[i, j] = (integrate(pt, b_mat[i, j], a_mat[i, j], df = fit.ash.t.u$result$df[i])$value) / (a_mat[i, j] - b_mat[i, j]) } else { Fjktrue[i, j] = pt(a_mat[i, j], df = fit.ash.t.u$result$df[i]) } } } Ftrue = Fjktrue %*% gtrue$pi</code></pre> <p>Plot the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> and ordered <span class="math inline">\(\left\{\hat F_{\left(j\right)}\right\} = \left\{\hat F_{(1)}, \ldots, \hat F_{(n)}\right\}\)</span>. Under goodness of fit, the histogram of <span class="math inline">\(\left\{\hat F_j\right\}\)</span> should look like <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> and <span class="math inline">\(\left\{\hat F_{(j)}\right\}\)</span> should look like a straight line from <span class="math inline">\(0\)</span> to <span class="math inline">\(1\)</span>. Oracle <span class="math inline">\(\left\{F_j\right\}\)</span> and <span class="math inline">\(\left\{F_{\left(j\right)}\right\}\)</span> under true <span class="math inline">\(g\)</span> are also plotted in the same way for comparison.</p> <pre class="r"><code>hist(Fhat, breaks = 20, xlab = expression(hat("F")[j]), prob = TRUE, main = expression(paste("Histogram of estimated ", hat("F")))) segments(0, 1, 1, 1, col = "red", lty = 2)</code></pre> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-15-1.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>hist(Ftrue, breaks = 20, xlab = expression("F"[j]), prob = TRUE, main = expression("Histogram of true F")) segments(0, 1, 1, 1, col = "red", lty = 2)</code></pre> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-15-2.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>hist(Fhat, breaks = 20, prob = TRUE, xlab = expression(paste("True ", "F"[j], " & Estimated ", hat("F")[j])), main = expression(paste("Histograms of F & ", hat("F"), " put together")), density = 10, angle = 45) hist(Ftrue, breaks = 20, prob = TRUE, add = TRUE, density = 10, angle = 135, border = "blue", col = "blue") legend(x = 0.5, y = par('usr')[4], legend = c("F", expression(hat("F"))), density = 10, angle = c(135, 45), border = c("blue", "black"), ncol = 2, bty = "n", text.col = c("blue", "black"), yjust = 0.75, fill = c("blue", "black"), xjust = 0.5) segments(0, 1, 1, 1, col = "red", lty = 2)</code></pre> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-15-3.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>par(mar = c(5.1, 5.1, 4.1, 2.1)) plot(sort(Fhat), cex = 0.25, pch = 19, xlab = "Order m", ylab = expression(paste("Ordered ", hat("F")["(m)"])), main = expression(paste("Ordered estimated ", hat("F")))) abline(-1/(n-1), 1/(n-1), col = "red")</code></pre> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-15-4.png" width="672" style="display: block; margin: auto;" /></p> <pre class="r"><code>plot(sort(Ftrue), cex = 0.25, pch = 19, xlab = "Order m", ylab = expression(paste("Ordered ", "F"["(m)"])), main = expression(paste("Ordered true ", "F"))) abline(-1/(n-1), 1/(n-1), col = "red")</code></pre> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-15-5.png" width="672" style="display: block; margin: auto;" /></p> </div> </div> <div id="exchangeability-assumption" class="section level2"> <h2>Exchangeability assumption</h2> <p>Now we are discussing several occasions when the diagnostic plots may show a conspicuous deviation from <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span>.</p> <p>The above numerical illustrations show that when data are generated exactly as <code>ASH</code>’s assumptions, <span class="math inline">\(\hat F_{j}\)</span> don’t deviate from <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> more so than <span class="math inline">\(F_{j}\)</span> do when we know the true exchangeable prior <span class="math inline">\(g\)</span>. This result indicates that <code>ASH</code> does a good job estimating <span class="math inline">\(\hat g\)</span>.</p> <p>However, how good is the exchangeability assumption for <span class="math inline">\(\beta_j\)</span>? If individual <span class="math inline">\(g_j\left(\beta_j\right)\)</span> are known, we can obtain the true <span class="math inline">\(F_{j}^o\)</span> (“o” stands for “oracle”) as</p> <p><span class="math display">\[ F_j^o = \int_{-\infty}^{\hat\beta_j}\int p\left(t\mid\beta_j, \hat s_j\right)g_j\left(\beta_j\right)d\beta_jdt \ . \]</span> Then the difference in the “uniformness” between <span class="math inline">\(F_j\)</span> and <span class="math inline">\(F_j^o\)</span> indicates the goodness of the exchangeability assumption.</p> <p>Here we are generating <span class="math inline">\(n = 10K\)</span> observations according to</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \ ;\\ \beta_j &\sim& 0.5\delta_0 + 0.5N(0, 1)\ ;\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1 &\sim& N\left(\beta_j, \hat s_j^2 \equiv1\right)\ . \end{array} \]</span> The histograms of <span class="math inline">\(\left\{F_j^o\right\}\)</span>, <span class="math inline">\(\left\{F_j\right\}\)</span>, and <span class="math inline">\(\left\{\hat F_j\right\}\)</span> are plotted together. In this example <span class="math inline">\(\left\{F_j^o\right\}\)</span> are hardly more uniform than <span class="math inline">\(\left\{F_j\right\}\)</span>.</p> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-21-1.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-21-2.png" width="672" style="display: block; margin: auto;" /></p> </div> <div id="unimodal-assumption" class="section level2"> <h2>Unimodal assumption</h2> <p>The <span class="math inline">\(n = 1K\)</span> observations are generated such that the unimodal assumption doesn’t hold.</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \ ;\\ \beta_j &\sim& 0.2\delta_0 + 0.4N(5, 1) + 0.4N(-5, 1)\ ;\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1 &\sim& N\left(\beta_j, \hat s_j^2 \equiv1\right)\ . \end{array} \]</span> The histograms of <span class="math inline">\(\left\{F_j\right\}\)</span>, and <span class="math inline">\(\left\{\hat F_j\right\}\)</span> are plotted together, as well as the ordered <span class="math inline">\(\left\{F_{(j)}\right\}\)</span> and <span class="math inline">\(\left\{\hat F_{(j)}\right\}\)</span>. <span class="math inline">\(\left\{\hat F_j\right\}\)</span> being conspicuously not uniform provides evidence for lack of goodness of fit.</p> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-26-1.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-26-2.png" width="672" style="display: block; margin: auto;" /></p> </div> <div id="mixture-misspecification" class="section level2"> <h2>Mixture misspecification</h2> <p>Even if the effect size prior <span class="math inline">\(g\)</span> is unimodal, because <code>ASH</code> implicitly makes the assumption that <span class="math inline">\(g\)</span> is sufficiently regular such that it can be approximated by a limited number of normals or uniforms, <code>ASH</code> can fail when the mixture components are not able to capture the true effect size distribution.</p> <p>In this example, the <span class="math inline">\(n = 1K\)</span> observations are generated, such that the true effect size distribution <span class="math inline">\(g\)</span> is uniform and thus can not be satisfactorily approximated by a mixture of normal. We’ll see what happens when the normal mixture prior is still used.</p> <p><span class="math display">\[ \begin{array}{rcl} \hat s_j &\equiv& 1 \ ;\\ \beta_j &\sim& \text{Unif}\left[-10, 10\right]\ ;\\ \hat\beta_j | \beta_j, \hat s_j \equiv 1 &\sim& N\left(\beta_j, \hat s_j^2 \equiv1\right)\ . \end{array} \]</span></p> <p>Let <span class="math inline">\(\hat F_{j}^n\)</span> be the estimated <span class="math inline">\(\hat F_{\hat\beta_j|\hat s_j}\left(\hat\beta_j \mid \hat s_j\right)\)</span> by <code>ASH</code> using normal mixtures (<code>mixcompdist = "normal"</code>), and <span class="math inline">\(\hat F_{j}^u\)</span> be that using uniform mixtures (<code>mixcompdist = "uniform"</code>). Both are plotted below, compared with <span class="math inline">\(F_{j}\)</span> using true exchangeable prior <span class="math inline">\(g = \text{Unif}\left[-10, 10\right]\)</span>.</p> <p>It can be seen that <code>ASH</code> using normal mixtures is not able to estimate <span class="math inline">\(g\)</span> well and thus is not producing <span class="math inline">\(\text{Unif}\left[0, 1\right]\)</span> <span class="math inline">\(\left\{\hat F_j\right\}\)</span>. <code>ASH</code> using uniform mixtures, on the contrary, is doing fine.</p> <p><img src="figure/diagnostic_plot.rmd/unnamed-chunk-33-1.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-33-2.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-33-3.png" width="672" style="display: block; margin: auto;" /><img src="figure/diagnostic_plot.rmd/unnamed-chunk-33-4.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 10.12.4 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] ashr_2.1.5 loaded via a namespace (and not attached): [1] Rcpp_0.12.10 lattice_0.20-34 codetools_0.2-15 [4] digest_0.6.11 foreach_1.4.3 rprojroot_1.2 [7] truncnorm_1.0-7 MASS_7.3-45 grid_3.3.3 [10] backports_1.0.5 git2r_0.18.0 magrittr_1.5 [13] evaluate_0.10 stringi_1.1.2 pscl_1.4.9 [16] doParallel_1.0.10 rmarkdown_1.3 iterators_1.0.8 [19] tools_3.3.3 stringr_1.2.0 parallel_3.3.3 [22] yaml_2.1.14 SQUAREM_2016.10-1 htmltools_0.3.5 [25] knitr_1.15.1 </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://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"; document.getElementsByTagName("head")[0].appendChild(script); })(); </script> </body> </html>