ABSTRACT

This chapter provides a brief discussion on common nonparametric statistical tests. The Wilcoxon rank sum test, also known as Mann-Whitney, is the nonparametric equivalent of the two-sample t-test. Specifically, the null hypothesis is that the distributions of the two groups are the same or differ by a shift of mu. The wilcox.test function requires the first two arguments to be the data sets. The default value of mu is 0. Spearman’s rank correlation test is performed using cor.test. The first two arguments are the two data sets. A nonparametric one-way Analysis of Variance is performed with kruskal.test. The chapter also includes exercise problems related to nonparametric statistical tests.