Kruskal–Wallis Test

One of the simplest designs in quantitative research involves the random allocation of a sample of N individuals to k different groups. The groups are exposed to different treatments, and the research question is whether there is any variation among the groups on some criterion variable. Classically, this question is addressed using the one-way between-subjects analysis of variance. However, this procedure assumes that the criterion variable in question (a) is measured on an interval or ratio scale, (b) is normally distributed, and (c) has the same variance in all of the groups. The Kruskal–Wallis one-way analysis of variance by ranks (to give the test its full name) was developed for use in situations in which one or more of these assumptions is not met. This ...