What Is the Mann-Whitney U Test?
The Mann-Whitney U test is the non-parametric alternative to the independent samples t-test. Instead of comparing means, it compares the rank distributions of two independent groups. It is used when the normality assumption cannot be met or when data are ordinal.
When to Use Mann-Whitney U
- The dependent variable is not normally distributed in one or both groups
- Data are measured on an ordinal scale (e.g., Likert items)
- Small sample sizes (n<30 per group)
- Significant outliers distort the mean
Running the Test in SPSS
Go to Analyze → Nonparametric Tests → Legacy Dialogs → 2 Independent Samples.
- Move the dependent variable to Test Variable List.
- Move the grouping variable to Grouping Variable and define the two group codes.
- Ensure Mann-Whitney U is selected under Test Type.
- Click OK.
Reading the Output
The Ranks table shows mean ranks per group — the higher mean rank indicates higher values in that group. The Test Statistics table provides the U statistic, z-value, and p-value. p<0.05 → a statistically significant difference exists between groups.
Effect Size: r
SPSS does not automatically report effect size for Mann-Whitney. Calculate it manually: r = z / √N. Interpretation: r=0.10 small, r=0.30 medium, r=0.50 large effect.
APA Reporting Example
A Mann-Whitney U test indicated that the intervention group (Mdn=78) had significantly higher scores than the control group (Mdn=65), U=924, z=-3.14, p=.002, r=.31.
Boss Statistics Support
Need help deciding between t-test and Mann-Whitney U, or writing up non-parametric results in APA format? Boss Statistics is here to help.