P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-26 11:18:02 +02:00
Code Releases Activity

(v1.8.1.9011) update prevalence of some genera

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2022-06-03 12:43:25 +02:00
parent 70a07bad39
commit 1b84564d36
35 changed files with 278 additions and 429 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/reference/g.test.html
View File

@ -17,7 +17,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">1.8.1.9009</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">1.8.1.9011</span>
</span>
</div>
@ -249,8 +249,8 @@
<p>Unlike the exact test of goodness-of-fit (<code><a href="https://rdrr.io/r/stats/fisher.test.html" class="external-link">fisher.test()</a></code>), the <em>G</em>-test does not directly calculate the probability of obtaining the observed results or something more extreme. Instead, like almost all statistical tests, the <em>G</em>-test has an intermediate step; it uses the data to calculate a test statistic that measures how far the observed data are from the null expectation. You then use a mathematical relationship, in this case the chi-square distribution, to estimate the probability of obtaining that value of the test statistic.</p>
<p>The <em>G</em>-test uses the log of the ratio of two likelihoods as the test statistic, which is why it is also called a likelihood ratio test or log-likelihood ratio test. The formula to calculate a <em>G</em>-statistic is:</p>
<p>\(G = 2 * sum(x * log(x / E))\)</p>
<p>where <code>E</code> are the expected values. Since this is chi-square distributed, the p value can be calculated in <span style="R">R</span> with:</p><div class="sourceCode"><pre><code><span class="va">p</span> <span class="op">&lt;-</span> <span class="fu">stats</span><span class="fu">::</span><span class="fu"><a href="https://rdrr.io/r/stats/Chisquare.html" class="external-link">pchisq</a></span><span class="op">(</span><span class="va">G</span>, <span class="va">df</span>, lower.tail <span class="op">=</span> <span class="cn">FALSE</span><span class="op">)</span></code></pre></div>
<p>where <code>E</code> are the expected values. Since this is chi-square distributed, the p value can be calculated in <span style="R">R</span> with:</p>
<p></p><div class="sourceCode"><pre><code></code></pre><p></p></div>
<p>where <code>df</code> are the degrees of freedom.</p>
<p>If there are more than two categories and you want to find out which ones are significantly different from their null expectation, you can use the same method of testing each category vs. the sum of all categories, with the Bonferroni correction. You use <em>G</em>-tests for each category, of course.</p>
</div>