7.3. Kruskal-Wallis Test
The Kruskal-Wallis (1952) test is a generalization of the two-sample Wilcoxon-Mann-Whitney test to three or more groups. It is a nonparametric test of the null hypothesis that the distribution of a response variable is the same in multiple independently sampled populations. The test requires an ordinally scaled response variable and is sensitive to the alternative hypothesis that there is a location difference among the populations. The Kruskal-Wallis test can be used whenever a one-way analysis of variance (ANOVA) model is appropriate.
When the sample sizes in the groups are small, tables of the exact distribution of the test statistic should be used. Alternatively, you can carry out exact tests of significance for ...
Get Categorical Data Analysis Using The SAS® System, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
