Bonferroni Test Statistic

In the testing of multiple comparisons in analysis of variance and regression analysis it is necessary to make allowance for the fact that the comparisons are not independent of one another. This allowance is made by multiplying the probability estimate by the number of comparisons involved. Also referred to as the Dunn multiple comparison test, although initially the test was proposed by R.A. Fisher.

Compiled by John P. Keeves 1995