Friedman ANOVA is also called two-way ANOVA for ranks, which is a nonparametric test that compares three or more paired groups.
Friedman ANOVA investigates the score differences between k treatments of n blocks. It can be used to answer the question whether the k samples come from the same population.
This example is taken from page 169 of Siegel (1956) Non-parametric Statistics for the Behavioral Sciences McGraw-Hill. The data relate to training scores of three matched treatments of 18 rats, trained under three different patterns of reinforcement.