Some of the more common statistical tests are listed here, according to the purposes for which they are used. Tests marked with an asterisk (*) are parametric and make more rigorous assumptions about the character of the data than do the non-parametric tests.

• Does the sample come from a specified population?

e.g. Chi square test for goodness of fit for a single sample Binomial test

• Are the scores of two unrelated samples different?

e.g. Chi square test for two independent samples Mann–Whitney U test

Student's t test for unmatched samples*

• Are the scores of two related samples different?

e.g. Wilcoxon matched-pairs test

Student's t test for matched samples*

• Are the scores of several unrelated samples different from each other?

e.g. Chi square test for more than two independent samples

Kruskal–Wallis one-way analysis of variance

Analysis of variance* (particularly when one variable may depend on two or more conditions)

• Are the scores of several related samples different from each other?

e.g. Friedman two-way analysis of variance

Repeated measures analysis of variance*

• Are two sets of scores associated?

e.g. Spearman correlation

Pearson correlation*

Simple regression* (when one variable may depend on another)

• Are several sets of scores associated?

e.g. Kendall coefficient of concordance

Multiple correlation*

Multiple regression* (when one variable may depend on others)

• Do more than one set of scores depend on more than one condition?

e.g. Multivariate analysis of variance*