Name of the test that controls alpha inflation when several means are being compared.

• A. t-test
• B. Chi-square
• C. ANOVA
• D. Mann-Whitney U

Answer: (C)

When you’re comparing several group means, the main concern is controlling the chance of a false positive across all those comparisons. ANOVA uses a single F-test to ask whether all the group means are equal, which keeps the overall alpha at the chosen level instead of letting it inflate if you did multiple two-sample tests. If that overall test is significant, you then look at specific differences with post-hoc comparisons that adjust for multiple testing (like Tukey or Bonferroni), so you can identify which means differ while still controlling the familywise error rate. The other tests aren’t designed for comparing more than two means at once: pairwise t-tests (or similar) would raise the false-positive rate with many comparisons, the Chi-square is for categorical data, and the Mann-Whitney U is for two independent groups in a nonparametric setting.