The best non-parametric alternative to two-way repeated measures ANOVA is the Friedman test. Here's why:
Non-parametric: The Friedman test doesn't assume normality or equal variances, making it a suitable alternative to traditional parametric tests.
Repeated measures: The Friedman test is designed for repeated measures designs, where the same subjects are measured multiple times.
Two-way: The Friedman test can handle two-way designs, examining the effects of two factors (e.g., time and treatment) on the outcome variable.
Robust: The Friedman test is robust to outliers and non-normality, making it a reliable choice for non-parametric analysis.
To perform the Friedman test, you can use statistical software like R, Python, or SPSS. The test produces a chi-squared statistic, which indicates whether there are significant differences between the groups.
If you need to explore post-hoc comparisons, you can use the Wilcoxon signed-rank test or the Conover test to examine pairwise differences between groups.
Remember to check the assumptions and requirements for the Friedman test, such as:
The data should be ordinal or continuous.
The sample size should be sufficient (at least 6-8 subjects per group).
The measurements should be independent (no carryover effects).
By using the Friedman test, you'll be able to analyze your two-way repeated measures data without worrying about parametric assumptions!
Thank you for your reply. I read it online at some sites that Friedman test is an alternative to one-way ANOVA which is why I was not confident to apply it and finding another method.