<< Click to Display Table of Contents >> Navigation:  Analysis of variance and covariance > Non-Parametric ANOVA

The methods described in the following subsections are similar to ANOVA procedures, but in each case do not require the same strict assumptions about the distribution of errors and related concerns of the former, parametric methods. This is achieved by analyzing the data ranks rather than the data themselves (Kruskal-Wallis and Friedman tests), and/or by using the median (Mood's median test) rather than the mean of the data.