Testing Hypotheses If Data Are Not Normal

If a dataset is not normal, or if it does not conform to the assumptions required for a t -test or analysis of variance (ANOVA), then a non-parametric test might be a good alternative. As with the tests, non-parametric tests also have a set of conditions that must be satisfied for the results of such a test to be valid. In this chapter, we discuss the use of the Wilcoxon signed-rank test as an alternative to the t -test and the Kruskal–Wallis test as an alternative to using an ANOVA. The use of a chi-square test, to understand whether the frequency of observations from different groups deviates significantly from one another, will also be discussed.