What is post-hoc testing and when is it used in ANOVA?

• A. Pairwise comparisons used after finding a significant F to determine which groups differ; methods include Tukey, Bonferroni.
• B. Pre-tests before ANOVA.
• C. Tests variance equality.
• D. Nonparametric alternative to ANOVA.

Answer: (B)

Post-hoc testing is a follow-up step conducted after an ANOVA shows a significant overall effect. ANOVA tells you that at least two group means differ, but it doesn’t reveal which specific groups are different. Post-hoc tests make those pairwise comparisons to identify exactly which groups differ, while controlling the risk of false positives across multiple comparisons. Common methods include Tukey’s Honestly Significant Difference test and Bonferroni-adjusted pairwise comparisons. These are used when you have more than two groups and you’ve found a significant F statistic, so you can determine where the differences lie. If the ANOVA isn’t significant, there’s no justification for post-hoc comparisons. Other concepts, like pre-testing before ANOVA, tests for equal variances, or nonparametric alternatives, address different aspects and aren’t about follow-up comparisons after a significant result.