f688dc8b0b0b4cff6962e70ebf6a16b4422b65ea gperez2 Tue Nov 17 10:54:53 2020 -0800 Fixed broken url diff --git src/hg/htdocs/goldenPath/help/qValue.html src/hg/htdocs/goldenPath/help/qValue.html index 6c5da82..22d25dc 100755 --- src/hg/htdocs/goldenPath/help/qValue.html +++ src/hg/htdocs/goldenPath/help/qValue.html @@ -1,28 +1,28 @@ <!DOCTYPE html> <!--#set var="TITLE" value="Genome Browser Q-Value" --> <!--#set var="ROOT" value="../.." --> <!-- Relative paths to support mirror sites with non-standard GB docs install --> <!--#include virtual="$ROOT/inc/gbPageStart.html" --> <h1>Q-Value</h1> <p> For any genome-wide analysis, reporting individual p-values can be misleading, because the p-value does not correct for the large number of tests performed. The q-value is an analog of the p-value that incorporates multiple testing correction. The q-value is defined as the minimum false discovery rate at which an observed score is deemed significant. Thus, the q-value attempts to control the percentage of false positives among a collection of scores. This contrasts with a traditional Bonferroni correction (or E-value), which controls the probability of one or more false positives in a collection of scores.</p> <p> Software for computing q-values from a collection of p-values is available at: -<a href="http://genomics.princeton.edu/storeylab/qvalue/" -target="_blank">http://genomics.princeton.edu/storeylab/qvalue</a></p> +<a href="https://github.com/StoreyLab/qvalue" +target="_blank">https://github.com/StoreyLab/qvalue</a></p> <p> For a good introduction to false discovery rate estimation and the q-value see: Storey JD, Tibshirani R. <a href="http://www.pnas.org/content/100/16/9440.abstract" target="_blank">Statistical significance for genomewide studies</a>. <em>Proc Natl Acad Sci</em>. 2003 Aug 5;100(16):9440-5.</p> <!--#include virtual="$ROOT/inc/gbPageEnd.html" -->