Mann–Whitney U Test and Kruskal–Wallis H Test Statistics in R

This chapterMann–Whitney U of the bookKruskal–Wallis H on statistical analysis covers how to analyze the effect of a variable over another by using the “Mann–Whitney U” and “Kruskal–Wallis H” tests in R. It explains and practically illustrates the differences and similarities between the Mann–Whitney UMann–Whitney U and Kruskal–Wallis HKruskal–Wallis H tests, including the various conditions that are required or necessary to performing the two different tests. The Mann-Whitney and Kruskall-Wallis tests are non-parametricNon-parametric equivalent and alternatives to the Independent t-tests and analysis of variance (ANOVA), respectively, used to analyze nominal/ordinal datasets or non-normally distributed datasets that violate the different test of assumptions or conditions for performing the parametric test or data sample sizes that are too small. By definition, Mann–Whitney test, also known as the U test, is used to determine the differences between two groups of an independent variable with no specific distributionDistribution on a single ranked scale and must be an ordinal variable data type. On the other hand, Kruskal–Wallis test, also referred to as H test, is described as an extension of the two-grouped Mann–Whitney U test used when the researcher or analysts are comparing more than two groups (i.e., three or more levels or categories) of independent samples and also uses ranked (ordinal) datasets. Whereas the Mann–Whitney U test is considered as a powerful alternative (i.e., non-parametricNon-parametric version) to the Independent t-test, the Kruskal–Wallis test is considered as the alternative (non-parametricNon-parametric version) to the One-way ANOVA test. Both the Mann–Whitney U and Kruskal–Wallis H tests are measured byRank scale considering the “medianMedian”.