Mann-Whitney U Test
The Mann-Whitney U test compares two independent samples by ranking all observations together and calculating U = n₁n₂ + n₁(n₁+1)/2 - R₁, where R₁ is the sum of ranks for the first group. Under H₀ of identical distributions, U follows a known distribution. The test requires only ordinal data.
Real World
A marketing team at Unilever compared customer satisfaction ratings between two packaging designs using the Mann-Whitney U test, since ratings on a 1–10 scale are ordinal rather than truly continuous.
Exam Focus
State hypotheses in terms of distributions or medians, not means — using 'mean' in a non-parametric test loses marks.
How well did you know this?