KRUSKELL-WALLIS test | DATA ANALYSIS #10
Kruskal-Wallis test. Data analysis #10. When to apply the Kruskal-Wallis test? Requirements for the initial data when applying the Kruskal-Wallis test, graphical representation, example, interpretation, algorithm of the Kruskal-Wallis test.
The Kruskal-Wallis test is designed to check the equality of the medians of several samples. This test is a multivariate generalization of the Wilcoxon-Mann-Whitney test. The Kruskal-Wallis test is a rank test, so it is invariant with respect to any monotone transformation of the measurement scale.
Also known as: Kruskal-Wallis H-test, Kruskal-Wallis one-way analysis of variance, Kruskal-Wallis test.
The Kruskal-Wallis test is a nonparametric alternative to univariate (between-subjects) analysis of variance. It is used to compare three or more samples, and tests the null hypotheses that the different samples were drawn from the same distribution, or from distributions with the same medians.
Thus, the interpretation of the Kruskal-Wallis test is basically the same as that of parametric univariate analysis of variance, except that this test is based on ranks rather than means. For more details, see Siegel & Castellan, 1988.
STATISTICS STATISTICA