Parametric and Non-Parametric Tests

Return to Behavioral Research Methods

Parametric Tests
Parametric tests are used when you have ratio or interval data. Parametric tests are more likely to detect significance.

Parametric tests include:


 * Correlation


 * Regression


 * Multiple Regression


 * T Tests


 * One-Way ANOVA


 * Two-Way ANOVA

Non-Parametric Tests
Non-parametric tests are used when you have nominal or ordinal data. Non-parametric tests are less likely to detect significance.

Never do a non-parametric test when you can do a parametric test. Non-parametric tests are not as powerful so it is much harder to find significant results.

Use non-parametric tests when:


 * (1) Your data is nominal or ordinal


 * (2) Your sample size is too small for a parametric test

Non-parametric tests include:


 * Chi-Square


 * Mann-Whitney U


 * Wilcoxon T Test


 * Kruskal-Wallis