Bonferroni correction is commonly applied after an ANOVA reveals a significant difference among groups, to control error across multiple comparisons. Which outcome remains the focus of this correction?

• A. Only two groups
• B. Multiple comparisons
• C. Effect size estimates
• D. Assumption violations

Answer: (B)

The key idea being tested is controlling the likelihood of false positives when you’re making several statistical tests at once after finding a difference with ANOVA. When ANOVA shows a significant difference among groups, you typically perform multiple pairwise comparisons to figure out which groups differ. Each test has its own chance of a false positive, and doing many tests increases the chance of at least one false positive across all comparisons. The Bonferroni correction addresses this by tightening the significance threshold across all these tests (often by dividing the overall alpha by the number of comparisons), so the overall risk of a Type I error remains at the desired level. That focus—reducing error across multiple comparisons—is why this correction is applied. It’s not about just two groups, it doesn’t adjust effect size estimates, and it doesn’t fix assumption violations.