What is the non-parametric test for comparing two independent samples?

What is the non-parametric test for comparing two independent samples?

• A. Mann-Whitney U
• B. Wilcoxon
• C. Kruskal-Wallis
• D. Friedman

Answer: (A)

When you’re comparing two independent groups without assuming a normal distribution, you look for a test that works with ranks rather than raw scores. The Mann-Whitney U test fits here because it converts all observations to ranks across both groups and then compares the sum of those ranks between the groups. This approach determines whether one group tends to have higher values than the other without relying on normality or equal variances, and it works well with small samples or ordinal data. Note that the Wilcoxon label can refer to a paired-sample test (the Wilcoxon signed-rank test) or, in some contexts, to a rank-sum approach, but for two independent samples the standard non-parametric option is Mann-Whitney U. Kruskal-Wallis is used when there are more than two independent groups, and Friedman is for repeated measures or related samples, so they’re not appropriate in this two-independent-samples scenario.

When you’re comparing two independent groups without assuming a normal distribution, you look for a test that works with ranks rather than raw scores. The Mann-Whitney U test fits here because it converts all observations to ranks across both groups and then compares the sum of those ranks between the groups. This approach determines whether one group tends to have higher values than the other without relying on normality or equal variances, and it works well with small samples or ordinal data.

Note that the Wilcoxon label can refer to a paired-sample test (the Wilcoxon signed-rank test) or, in some contexts, to a rank-sum approach, but for two independent samples the standard non-parametric option is Mann-Whitney U. Kruskal-Wallis is used when there are more than two independent groups, and Friedman is for repeated measures or related samples, so they’re not appropriate in this two-independent-samples scenario.