Non parametric tests are used when the data does not follow know distribution such as the normal distribution. It is ideal for testing differences between categorical data or ranked data.

Mann-Whitney U-Test

Used to tests whether two samples have the same parent distribution and medians. The Mann-Whitney U-Test is the non-parametric equivalent of the t-Test.

Kruskal-Wallis One Way Analysis by Ranks

Used to test whether two or more samples come from populations having the same parent distribution and medians. The Kruskal-Wallis Test is the non-parametric equivalent of the Single Factor Analysis of Variance (ANOVA).

Friedman’s Two Way Analysis by Ranks

Used to tests whether two or more treatments come from populations having the same parent distribution and medians.

Wilcoxon’s Signed Rank Test

Tests whether the paired observations in sample A and sample B are significantly different. Non Parametric equivalent to the paired t-Test.