SPSS guide
t-test or ANOVA: which should I use?
Short answer
Use a t-test to compare two groups or two conditions. Use an ANOVA to compare three or more. With exactly two groups they give the same answer (F equals t squared), but running several t-tests instead of one ANOVA inflates your chance of a false positive.
Why not just run several t-tests?
Every test at α = .05 carries a 5% risk of a false positive. With three groups you’d need three t-tests, and the chance of at least one false positive rises to about 14%. ANOVA tests all the groups at once, then post hoc tests compare pairs with a correction.
Which version do you need?
- Two separate groups: independent-samples t-test.
- Same people measured twice: paired-samples t-test.
- Three or more separate groups: one-way ANOVA.
- Same people in three or more conditions: repeated-measures ANOVA.
- Two grouping variables at once: two-way ANOVA.
- A repeated factor plus a grouping factor: mixed ANOVA.
After the ANOVA
A significant F only says that at least one group differs. Use post hoc tests (Tukey, or Games-Howell when variances differ) to find out which.
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.