In the context of multiple testing, Bonferroni correction is described as a method to

In the context of multiple testing, Bonferroni correction is described as a method to

• A. Increase alpha for all tests
• B. Control for Type I error
• C. Adjust sample size
• D. Modify effect size

Answer: (B)

When you run many statistical tests, the chance of getting at least one false positive grows. Bonferroni correction addresses this by controlling the overall, or family-wise, Type I error rate across all tests. It does this by making each individual test harder to reach significance: you set the per-test significance level to the overall alpha divided by the number of tests. For example, with an overall alpha of 0.05 and 10 tests, each test uses a threshold of 0.005. This keeps the probability of any false positive among all tests at or below 0.05. It doesn’t increase alpha, nor does it adjust sample size or the true effect size; it just changes the decision threshold to protect against false positives. It’s a conservative approach, especially when many tests are involved or when tests are not independent.

When you run many statistical tests, the chance of getting at least one false positive grows. Bonferroni correction addresses this by controlling the overall, or family-wise, Type I error rate across all tests. It does this by making each individual test harder to reach significance: you set the per-test significance level to the overall alpha divided by the number of tests. For example, with an overall alpha of 0.05 and 10 tests, each test uses a threshold of 0.005. This keeps the probability of any false positive among all tests at or below 0.05. It doesn’t increase alpha, nor does it adjust sample size or the true effect size; it just changes the decision threshold to protect against false positives. It’s a conservative approach, especially when many tests are involved or when tests are not independent.