Wilcoxon's rank-sum test is ...

Wilcoxon's rank-sum test is ...

• A. A non-parametric test for differences between two independent samples, equivalent to the Mann-Whitney test.
• B. A non-parametric test for differences between two independent samples, separate from Mann-Whitney.
• C. A parametric test for differences between two related samples.
• D. A test for equality of variances.

Answer: (A)

Wilcoxon's rank-sum test is a nonparametric method for comparing two independent samples. It doesn’t assume normality, so it’s used when data are skewed or ordinal. The test works by ranking all observations from both groups together and then comparing the sum of ranks from each group. If the two populations have the same distribution, the rank sums should be similar; a large difference suggests one group tends to have higher values than the other. Because it relies on ranks rather than raw scores, it’s robust to outliers and nonnormal shapes. This approach is mathematically the same as the Mann-Whitney U test, just different formulations of the same idea. It isn’t used for related samples (that would be the Wilcoxon signed-rank test) and it doesn’t assess equality of variances.

Wilcoxon's rank-sum test is a nonparametric method for comparing two independent samples. It doesn’t assume normality, so it’s used when data are skewed or ordinal. The test works by ranking all observations from both groups together and then comparing the sum of ranks from each group. If the two populations have the same distribution, the rank sums should be similar; a large difference suggests one group tends to have higher values than the other. Because it relies on ranks rather than raw scores, it’s robust to outliers and nonnormal shapes. This approach is mathematically the same as the Mann-Whitney U test, just different formulations of the same idea. It isn’t used for related samples (that would be the Wilcoxon signed-rank test) and it doesn’t assess equality of variances.