Independent-samples nonparametric tests (automatic)
Compares groups on each test field: Mann-Whitney U for two groups, Kruskal-Wallis for more (with Bonferroni-adjusted pairwise comparisons when significant).
Menu: Analyze → Nonparametric Tests → Independent Samples…
When should I use it?
- Comparing ratings or skewed scores across groups without assuming normality.
What are the assumptions?
- Independent groups; ordinal or scale test fields.
How do I run it in StatLab?
- Move the outcomes to Test fields and the grouping variable to Groups.
How do I read the output?
| Output | Meaning |
|---|---|
| Hypothesis Test Summary | Decision per field. |
| Pairwise Comparisons | Shown for significant Kruskal-Wallis tests; read Adj. Sig. |
Worked example
On the practice survey dataset (File → Sample dataset), this command — which the dialog's Paste button also produces — runs the procedure:
PROC npIndependent /vars=(score age) /group=group /alpha=0.05 /details=NO.
Output tables: Hypothesis Test Summary.
Computed by StatLab's validated procedure code when this page was built. The example only illustrates the steps; choose variables that fit your own research question.
What are common mistakes?
- Reading unadjusted pairwise Sig. values.