In which circumstance would you use the Friedman's Test?

Friedman's Test is a non-parametric statistical test utilized primarily in situations where you are dealing with repeated measures on the same subjects. It serves as an alternative to the parametric ANOVA when the assumptions of normality are violated. This makes it particularly useful when the data do not conform to the normal distribution required for traditional parametric tests.

In this context, choosing the scenario where data violates normality assumptions is appropriate for Friedman's Test, as it allows researchers to accurately assess differences in paired or related groups without relying on the normality assumption. By using this test, researchers can still derive meaningful insights from their ordinal data or continuous data that do not meet the normal distribution criteria, rendering it a robust option under such conditions.

Other options relate to different types of analyses or conditions which are not suitable for the application of Friedman's Test. For example, comparing independent samples typically requires a different test such as the Kruskal-Wallis H test or a t-test, and large sample sizes might allow for the use of parametric tests given that the Central Limit Theorem can justify normality in means with sufficient sample size. Categorical data often does not fit the requirements for applying Friedman's Test, as it is instead designed for ordinal or continuous data