Dunn–Bonferroni procedure
a statistical method for assessing whether multiple pairs of samples are significantly different from each other, while protecting the overall Type I error rate by dividing the alpha or significance level by the number of comparisons made. For example, if a researcher wants to investigate whether three samples are significantly different using an alpha of .05, three t tests could be conducted (i.e., between groups 1 and 2, 2 and 3, and 1 and 3) using an alpha level of .05/3 = .0167 for each comparison; this approach would hold the overall Type I error rate at .05. Also called Bonferroni t test; Dunn’s multiple comparison test. [Olive Jean Dunn, U.S. mathematician; Carlo Emilio Bonferroni (1892–1960), Italian mathematician]