Multiple test correction: Bonferroni, FDR

Multiple test correction methods are used to control the increased risk of Type I errors (false positives) when performing multiple statistical tests simultaneously. Multiple testing corrections adjust p-values derived from multiple statistical tests to correct for occurrence of false positives.

Watch this video to take a closer look at Type I and Type II errors:

The Bonferroni correction

The Bonferroni correction is a straightforward and conservative approach that adjusts the significance level by dividing it by the number of tests performed. This reduces the likelihood of false positives but can also increase the risk of Type II errors (false negatives) due to its stringent nature.

The False Discovery Rate

The False Discovery Rate (FDR) method, such as the Benjamini-Hochberg procedure, is a less conservative approach that controls the expected proportion of false positives among the rejected hypotheses. FDR methods are more powerful than the Bonferroni correction, allowing for the identification of more true positives while still controlling for false discoveries. This makes FDR particularly useful in large-scale testing scenarios, such as genomic studies, where a large number of tests are conducted simultaneously.