Chapter 14. The Kruskal-Wallis Test
14.1 Introduction 273
14.2 Synopsis 273
14.3 Examples 275
14.4 Details & Notes 279
The Kruskal-Wallis test is a non-parametric analogue of the one-way ANOVA (Chapter 6). It is used to compare population location parameters (mean, median, etc.) among two or more groups based on independent samples. Unlike an ANOVA, the assumption of normally distributed responses is not necessary. The Kruskal-Wallis test is an extension of the Wilcoxon rank-sum test (Chapter 13) for more than two groups, just as a one-way ANOVA is an extension of the two-sample t-test.
The Kruskal-Wallis test is based on the ranks of the data. This test is often useful in clinical trials for comparing responses among three or more ...