MEGA

TABLE

Easy
Post-hoc Tests
SPSS
Free

You run a one-way ANOVA in SPSS to compare average weekly caffeine intake (mg) across 3 groups (No coffee, 1–2 cups/day, 3+ cups/day). You get:

SPSS: Test of Homogeneity of Variances (Levene’s Test) Sig. = .012

And the ANOVA is significant (p < .05). Which post-hoc test is MOST appropriate to report in SPSS?

A

Tukey HSD, because it assumes equal variances

B

Games-Howell, because it does not assume equal variances

C

Fisher’s LSD, because it is always the safest choice after ANOVA

D

No post-hoc test is allowed when Levene’s test is significant