Assignment%20II/output/report.html

<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
<meta name="generator" content="litedown 0.7">
<title></title>
<style type="text/css">
body {
  font-family: sans-serif;
  max-width: 800px;
  margin: auto;
  padding: 1em;
  line-height: 1.5;
  print-color-adjust: exact;
  -webkit-print-color-adjust: exact;
}
body, .abstract, code, .footnotes, footer, #refs, .caption { font-size: .9em; }
li li { font-size: .95em; }
ul:has(li > input[type="checkbox"]) { list-style: none; padding-left: 1em; }
*, :before, :after { box-sizing: border-box; }
a { color: steelblue; }
pre, img { max-width: 100%; }
pre { white-space: pre-wrap; word-break: break-word; }
pre code { display: block; padding: 1em; overflow-x: auto; }
code { font-family: 'DejaVu Sans Mono', 'Droid Sans Mono', 'Lucida Console', Consolas, Monaco, monospace; }
:not(pre, th) > code, code[class], div > .caption { background: #f8f8f8; }
pre > code:is(:not([class]), .language-plain, .language-none, .plain), .box, .figure, .table { background: inherit; border: 1px solid #eee; }
pre > code {
  &.message { border-color: #9eeaf9; }
  &.warning { background: #fff3cd; border-color: #fff3cd; }
  &.error { background: #f8d7da; border-color: #f8d7da; }
}
.fenced-chunk { border-left: 1px solid #666; }
.code-fence {
  opacity: .4;
  border: 1px dashed #666;
  border-left: 2px solid;
  &:hover { opacity: inherit; }
}
.box, .figure, .table, table { margin: 1em auto; }
div > .caption { padding: 1px 1em; }
.figure { p:has(img, svg), pre:has(svg) { text-align: center; } }
.flex-col { display: flex; justify-content: space-between; }
table {
  &:only-child:not(.table > *) { margin: auto; }
  th, td { padding: 5px; font-variant-numeric: tabular-nums; }
  thead, tfoot, tr:nth-child(even) { background: whitesmoke; }
  thead th { border-bottom: 1px solid #ddd; }
  &:not(.datatable-table) {
    border-top: 1px solid #666;
    border-bottom: 1px solid #666;
  }
}
blockquote {
  color: #666;
  margin: 0;
  padding: 1px 1em;
  border-left: .5em solid #eee;
}
hr, .footnotes::before { border: 1px dashed #ddd; }
.frontmatter { text-align: center; }
#TOC {
  a { text-decoration: none; }
  ul { list-style: none; padding-left: 1em; }
  & > ul { padding: 0; }
  ul ul { border-left: 1px solid lightsteelblue; }
}
.body h2 { border-bottom: 1px solid #666; }
.body .appendix, .appendix ~ h2 { border-bottom-style: dashed; }
.main-number::after { content: "."; }
span[class^="ref-number-"] { font-weight: bold; }
.ref-number-fig::after, .ref-number-tab::after { content: ":"; }
.cross-ref-chp::before { content: "Chapter "; }
.cross-ref-sec::before { content: "Section "; }
.cross-ref-fig::before, .ref-number-fig::before { content: "Figure "; }
.cross-ref-tab::before, .ref-number-tab::before { content: "Table "; }
.cross-ref-eqn::before, .MathJax_ref:has(mjx-mtext > mjx-c + mjx-c)::before { content: "Equation "; }
.abstract, #refs {
  &::before { display: block; margin: 1em auto; font-weight: bold; }
}
.abstract::before { content: "Abstract"; text-align: center; }
#refs::before { content: "Bibliography"; font-size: 1.5em; }
.ref-paren-open::before { content: "("; }
.ref-paren-close::after { content: ")"; }
.ref-semicolon::after { content: "; "; }
.ref-and::after { content: " and "; }
.ref-et-al::after { content: " et al."; font-style: italic; }
.footnote-ref a {
  &::before { content: "["; }
  &::after { content: "]"; }
}
section.footnotes {
  margin-top: 2em;
  &::before { content: ""; display: block; max-width: 20em; }
}
.fade {
  background: repeating-linear-gradient(135deg, white, white 30px, #ddd 32px, #ddd 32px);
  opacity: 0.6;
}

@media print {
  body { max-width: 100%; }
  tr, img { break-inside: avoid; }
}
@media only screen and (min-width: 992px) {
  body:not(.pagesjs) pre:has(.line-numbers):not(:hover) { white-space: pre; }
}
</style>
</head>
<body>
<div class="frontmatter">
</div>
<div class="body">
<h1 id="chp:exploratory-data-analysis-and-models-on-the-epi-dataset">exploratory data analysis and models on the epi dataset</h1>
<p>date: 2025-10-13</p>
<h2 id="sec:dataset-and-choices">dataset and choices</h2>
<ul>
<li><strong>file</strong>: <code>epi_results_2024_pop_gdp_v2.csv</code></li>
<li><strong>region column</strong>: <code>region</code></li>
<li><strong>response var</strong>: <code>EPI.new</code></li>
<li><strong>regions</strong>: <code>Sub-Saharan Africa</code> vs <code>Latin America &amp; Caribbean</code></li>
</ul>
<h2 id="sec:1-variable-distributions">1) variable distributions</h2>
<h3 id="sec:1-1-boxplots-and-histograms-with-density">1.1 boxplots and histograms (with density!)</h3>
<p><img src="data:image/png;base64,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
<img src="data:image/png;base64,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
<img src="data:image/png;base64,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
<img src="data:image/png;base64,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
<h3 id="sec:1-2-qq-plot-two-sample">1.2 qq plot (two-sample)</h3>
<p><img src="data:image/png;base64,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
<h2 id="sec:2-linear-models">2) linear models</h2>
<h3 id="sec:full-epi-new-gdp">full: EPI.new ~ gdp</h3>
<h3 id="sec:full-epi-new-gdp-population">full: EPI.new ~ gdp + population</h3>
<h3 id="sec:2-2-same-models-on-one-region-comparison">2.2 same models on one region (comparison)</h3>
<p>on region <code>Sub-Saharan Africa</code>, the better model is <strong>region Sub-Saharan Africa: EPI.new ~ gdp + population</strong> (r²=0.361, aic=265.4, bic=272.7).</p>
<h2 id="sec:3-classification-knn-label-region">3) classification (knn, label = region)</h2>
<h3 id="sec:model-a">model A</h3>
<ul>
<li><strong>k</strong>: 5  |  <strong>accuracy</strong>: 0.5581  |  <strong>test n</strong>: 43
variables: <code>c(&quot;AGR.new&quot;, &quot;AIR.new&quot;, &quot;APO.new&quot;)</code>
<img src="data:image/png;base64,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
</ul>
<h3 id="sec:model-b">model B</h3>
<ul>
<li><strong>k</strong>: 5  |  <strong>accuracy</strong>: 0.5116  |  <strong>test n</strong>: 43
variables: <code>c(&quot;BCA.new&quot;, &quot;BDH.new&quot;, &quot;CBP.new&quot;)</code>
<img src="data:image/png;base64,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
</ul>
</div>
</body>
</html>