SPSS guide

Levene’s test is significant: what now?

Short answer

A significant Levene’s test (p < .05) means the groups have different variances. For a t-test, read the “Equal variances not assumed” row. For a one-way ANOVA, report Welch’s ANOVA with Games-Howell post hoc tests. Both are already in the standard SPSS dialogs.

By analysis

  • Independent-samples t-test: use the second row of the output (Welch’s t-test). Its df won’t be a whole number.
  • One-way ANOVA: tick Welch under Options and Games-Howell under Post Hoc.
  • Two-way or mixed ANOVA: there’s no Welch option. With roughly equal group sizes the F test is fairly robust; otherwise consider transforming the outcome or a robust alternative, and say what you did.

Don’t panic about tiny differences

With large samples Levene’s test can flag small, harmless differences. Look at the SDs too: a common rule of thumb is to worry when the largest group variance is more than about four times the smallest.

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.

More SPSS questions

All SPSS tutorials →