False positive rate

False positive rate


When performing multiple comparisons in a statistical analysis, the false positive rate is the probability of falsely rejecting the null hypothesis for a particular test among all the tests performed. If the false positive rate is a constant α for all tests performed, it can also be interpreted as the expected proportion among all tests performed that are false positives (also known as type 1 errors).

In the setting of analysis of variance (ANOVA), the false positive rate is referred to as the comparisonwise error rate or pairwise error rate. When three or more treatments are studied in parallel, a comparison can be made for each pair of treatments to assess whether one of the treatments is superior to the other. For example, if three treatments are studied, there are three pairwise comparisons among them.

The false positive rate is very different from the familywise error rate, which is the probability that at least one of the tests that are performed results in a type I error. As the number of tests grows, the familywise error rate generally tends to 1 even while the false positive rate remains fixed.