Although nonparametric methods can be used to analyze dependent variables that naturally occur on an ordinal scale, they are more commonly used to analyze continuous dependent variables converted to an ordinal scale to circumvent assumptions of a Gaussian sampling distribution or equality of variances. This conversion involves representing continuous data with their relative ranks. When we have an ordinal dependent variable and no independent variables, we use the Wilcoxon Signed-Rank test. In the Wilcoxon Signed-Rank test we rank the absolute values of the differences in observations and sum the ranks for the positive and for the negative differences. The Wilcoxon Signed-Rank statistic is the smaller of the two. It is compared to critical values. When we have an ordinal dependent variable and one nominal independent variable we can use either the Wilcoxon Rank-Sum test or the Mann-Whitney test. Both tests give us the same result. It is the Mann-Whitney test we examine in this chapter. We calculate two values in this test and select the larger of the two to compare to a critical value. When we have an ordinal dependent variable and an ordinal independent variable (or continuous data converted to a scale of ranks) we are interested in the strength of the association between the variables. Most often, we use Spearman’s correlation analysis to examine the association. When we have an ordinal dependent variable and more than one nominal independent variable, we analyze the data using the Kruskal-Wallis test. This can be either one-way if the groups represent categories of one characteristic or factorial if the groups represent categories of more than one characteristic.