nmode's Git Repositories - Rnaught/blob - articles/seq_bayes_post.html

   1 <!DOCTYPE html>
   2 <!-- Generated by pkgdown: do not edit by hand --><html lang="en">
   3 <head>
   4 <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
   5 <meta charset="utf-8">
   6 <meta http-equiv="X-UA-Compatible" content="IE=edge">
   7 <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
   8 <title>Sequential Bayes: Utilizing the Posterior Distribution • Rnaught</title>
   9 <!-- favicons --><link rel="icon" type="image/png" sizes="16x16" href="../favicon-16x16.png">
  10 <link rel="icon" type="image/png" sizes="32x32" href="../favicon-32x32.png">
  11 <link rel="apple-touch-icon" type="image/png" sizes="180x180" href="../apple-touch-icon.png">
  12 <link rel="apple-touch-icon" type="image/png" sizes="120x120" href="../apple-touch-icon-120x120.png">
  13 <link rel="apple-touch-icon" type="image/png" sizes="76x76" href="../apple-touch-icon-76x76.png">
  14 <link rel="apple-touch-icon" type="image/png" sizes="60x60" href="../apple-touch-icon-60x60.png">
  15 <script src="../deps/jquery-3.6.0/jquery-3.6.0.min.js"></script><meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
  16 <link href="../deps/bootstrap-5.3.1/bootstrap.min.css" rel="stylesheet">
  17 <script src="../deps/bootstrap-5.3.1/bootstrap.bundle.min.js"></script><link href="../deps/font-awesome-6.5.2/css/all.min.css" rel="stylesheet">
  18 <link href="../deps/font-awesome-6.5.2/css/v4-shims.min.css" rel="stylesheet">
  19 <script src="../deps/headroom-0.11.0/headroom.min.js"></script><script src="../deps/headroom-0.11.0/jQuery.headroom.min.js"></script><script src="../deps/bootstrap-toc-1.0.1/bootstrap-toc.min.js"></script><script src="../deps/clipboard.js-2.0.11/clipboard.min.js"></script><script src="../deps/search-1.0.0/autocomplete.jquery.min.js"></script><script src="../deps/search-1.0.0/fuse.min.js"></script><script src="../deps/search-1.0.0/mark.min.js"></script><!-- pkgdown --><script src="../pkgdown.js"></script><meta property="og:title" content="Sequential Bayes: Utilizing the Posterior Distribution">
  20 </head>
  21 <body>
  22     <a href="#main" class="visually-hidden-focusable">Skip to contents</a>
  23
  24
  25     <nav class="navbar navbar-expand-lg fixed-top bg-light" data-bs-theme="light" aria-label="Site navigation"><div class="container">
  26
  27     <a class="navbar-brand me-2" href="../index.html">Rnaught</a>
  28
  29     <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">0.1.0</small>
  30
  31
  32     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
  33       <span class="navbar-toggler-icon"></span>
  34     </button>
  35
  36     <div id="navbar" class="collapse navbar-collapse ms-3">
  37       <ul class="navbar-nav me-auto">
  38 <li class="nav-item"><a class="nav-link" href="../articles/Rnaught.html">Get started</a></li>
  39 <li class="nav-item"><a class="nav-link" href="../reference/index.html">Reference</a></li>
  40 <li class="active nav-item dropdown">
  41   <button class="nav-link dropdown-toggle" type="button" id="dropdown-articles" data-bs-toggle="dropdown" aria-expanded="false" aria-haspopup="true">Articles</button>
  42   <ul class="dropdown-menu" aria-labelledby="dropdown-articles">
  43 <li><a class="dropdown-item" href="../articles/seq_bayes_post.html">Sequential Bayes: Utilizing the Posterior Distribution</a></li>
  44     <li><a class="dropdown-item" href="../articles/wp_serial.html">White and Pagano: Utilizing the Serial Distribution</a></li>
  45   </ul>
  46 </li>
  47       </ul>
  48 <ul class="navbar-nav">
  49 <li class="nav-item"><form class="form-inline" role="search">
  50  <input class="form-control" type="search" name="search-input" id="search-input" autocomplete="off" aria-label="Search site" placeholder="Search for" data-search-index="../search.json">
  51 </form></li>
  52 <li class="nav-item"><a class="external-link nav-link" href="https://github.com/MI2YorkU/Rnaught/" aria-label="GitHub"><span class="fa fab fa-github fa-lg"></span></a></li>
  53       </ul>
  54 </div>
  55
  56
  57   </div>
  58 </nav><div class="container template-article">
  59
  60
  61
  62
  63 <div class="row">
  64   <main id="main" class="col-md-9"><div class="page-header">
  65       <img src="../logo.svg" class="logo" alt=""><h1>Sequential Bayes: Utilizing the Posterior Distribution</h1>
  66
  67
  68       <small class="dont-index">Source: <a href="https://github.com/MI2YorkU/Rnaught/blob/master/vignettes/seq_bayes_post.Rmd" class="external-link"><code>vignettes/seq_bayes_post.Rmd</code></a></small>
  69       <div class="d-none name"><code>seq_bayes_post.Rmd</code></div>
  70     </div>
  71
  72
  73
  74 <p>In the Sequential Bayes method, the probability distribution of R0 is
  75 updated sequentially from one case count to the next, starting from a
  76 (discretized) uniform prior. By default, the function
  77 <code><a href="../reference/seq_bayes.html">seq_bayes()</a></code> returns the mean of the last updated posterior
  78 distribution as its estimate of R0. However, by setting the parameter
  79 <code>post</code> to <code>TRUE</code>, it is possible to return the
  80 final distribution itself:</p>
  81 <div class="sourceCode" id="cb1"><pre class="downlit sourceCode r">
  82 <code class="sourceCode R"><span><span class="co"># Daily case counts.</span></span>
  83 <span><span class="va">cases</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://rdrr.io/r/base/c.html" class="external-link">c</a></span><span class="op">(</span><span class="fl">1</span>, <span class="fl">4</span>, <span class="fl">10</span>, <span class="fl">5</span>, <span class="fl">3</span>, <span class="fl">4</span>, <span class="fl">19</span>, <span class="fl">3</span>, <span class="fl">3</span>, <span class="fl">14</span>, <span class="fl">4</span><span class="op">)</span></span>
  84 <span></span>
  85 <span><span class="va">posterior</span> <span class="op">&lt;-</span> <span class="fu"><a href="../reference/seq_bayes.html">seq_bayes</a></span><span class="op">(</span><span class="va">cases</span>, mu <span class="op">=</span> <span class="fl">8</span>, kappa <span class="op">=</span> <span class="fl">7</span>, post <span class="op">=</span> <span class="cn">TRUE</span><span class="op">)</span></span></code></pre></div>
  86 <p>First, the distribution can be used to retrieve the original estimate
  87 (had <code>post</code> been left to its default value of
  88 <code>FALSE</code>) by calculating its mean:</p>
  89 <div class="sourceCode" id="cb2"><pre class="downlit sourceCode r">
  90 <code class="sourceCode R"><span><span class="co"># `supp` is the support of the distribution, and `pmf` is its probability mass</span></span>
  91 <span><span class="co"># function.</span></span>
  92 <span><span class="va">post_mean</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://rdrr.io/r/base/sum.html" class="external-link">sum</a></span><span class="op">(</span><span class="va">posterior</span><span class="op">$</span><span class="va">supp</span> <span class="op">*</span> <span class="va">posterior</span><span class="op">$</span><span class="va">pmf</span><span class="op">)</span></span>
  93 <span><span class="va">post_mean</span></span>
  94 <span><span class="co">#&gt; [1] 1.476652</span></span>
  95 <span></span>
  96 <span><span class="co"># Verify that the following is true:</span></span>
  97 <span><span class="va">post_mean</span> <span class="op">==</span> <span class="fu"><a href="../reference/seq_bayes.html">seq_bayes</a></span><span class="op">(</span><span class="va">cases</span>, mu <span class="op">=</span> <span class="fl">8</span>, kappa <span class="op">=</span> <span class="fl">7</span><span class="op">)</span></span>
  98 <span><span class="co">#&gt; [1] TRUE</span></span></code></pre></div>
  99 <p>Another use of the posterior is to obtain an alternative estimate of
 100 R0. For instance, the following extracts the posterior mode rather than
 101 the mean:</p>
 102 <div class="sourceCode" id="cb3"><pre class="downlit sourceCode r">
 103 <code class="sourceCode R"><span><span class="va">post_mode</span> <span class="op">&lt;-</span> <span class="va">posterior</span><span class="op">$</span><span class="va">supp</span><span class="op">[</span><span class="fu"><a href="https://rdrr.io/r/base/which.min.html" class="external-link">which.max</a></span><span class="op">(</span><span class="va">posterior</span><span class="op">$</span><span class="va">pmf</span><span class="op">)</span><span class="op">]</span></span>
 104 <span><span class="va">post_mode</span></span>
 105 <span><span class="co">#&gt; [1] 1.36</span></span></code></pre></div>
 106 <p>Returning the posterior is suitable for visualization purposes. Below
 107 is a graph containing the uniform prior, final posterior distribution,
 108 posterior mean and posterior mode:</p>
 109 <p><img src="seq_bayes_post_files/figure-html/unnamed-chunk-5-1.png" width="1400"></p>
 110   </main>
 111 </div>
 112
 113
 114
 115     <footer><div class="pkgdown-footer-left">
 116   <p>Developed by Naeem Model, Sawitree Boonpatcharanon, Jane Heffernan, Hanna Jankowski.</p>
 117 </div>
 118
 119 <div class="pkgdown-footer-right">
 120   <p>Site built with <a href="https://pkgdown.r-lib.org/" class="external-link">pkgdown</a> 2.1.1.</p>
 121 </div>
 122
 123     </footer>
 124 </div>
 125
 126
 127
 128
 129
 130   </body>
 131 </html>