PMCMR: Calculate Pairwise Multiple Comparisons of Mean Rank Sums

The Kruskal and Wallis one-way analysis of variance by ranks or van der Waerden's normal score test can be employed, if the data do not meet the assumptions for one-way ANOVA. Provided that significant differences were detected by the omnibus test, one may be interested in applying post-hoc tests for pairwise multiple comparisons (such as Nemenyi's test, Dunn's test, Conover's test, van der Waerden's test). Similarly, one-way ANOVA with repeated measures that is also referred to as ANOVA with unreplicated block design can also be conducted via the Friedman-Test or the Quade-test. The consequent post-hoc pairwise multiple comparison tests according to Nemenyi, Conover and Quade are also provided in this package. Finally Durbin's test for a two-way balanced incomplete block design (BIBD) is also given in this package.

AuthorThorsten Pohlert
Date of publication2016-01-06 10:15:27
MaintainerThorsten Pohlert <>
LicenseGPL (>= 3)

View on CRAN

Questions? Problems? Suggestions? or email at

All documentation is copyright its authors; we didn't write any of that.