SPSS guide
Parametric vs non-parametric tests
Short answer
Parametric tests (t-tests, ANOVA, Pearson, regression) assume Scale data that are roughly normal. Non-parametric tests work on ranks, so they suit ordinal data and data that clearly break those assumptions. When the assumptions are met, parametric tests are more powerful.
The non-parametric alternative to each test
- Independent-samples t-test → Mann-Whitney U.
- Paired-samples t-test → Wilcoxon signed-rank.
- One-way ANOVA → Kruskal-Wallis H.
- Repeated-measures ANOVA → Friedman.
- Pearson correlation → Spearman’s rho (or Kendall’s tau-b).
How to decide
Check the level of measurement first: ordinal outcomes go non-parametric. For Scale data, look at histograms, Q-Q plots and Shapiro-Wilk in each group. In large samples (30+ per group) t-tests and ANOVA cope well with mild non-normality, so rely on plots more than on the test.
How the write-up changes
Report medians rather than means, the test statistic (U, z, H or χ²), the exact p and an effect size such as r = |z| ÷ √N.
Step-by-step tutorials
Still not sure which test fits?
Answer a few questions and the free tool tells you the test, the SPSS menu path and an APA example.