In a study of five different outcomes, the researcher wants to keep the overall type I error at 0.05 using the Bonferroni method. What significance threshold should be used for each test?
Answer and explanation
Correct answer: B. 0.01
- Step 1: Bonferroni divides alpha by the number of comparisons.
- Step 2: 0.05 divided by 5 is 0.01.
Answer
0.01.
Why not the others: 0.05: 0.05 does not correct for multiple testing. 0.25: 0.25 multiplies instead of dividing. 0.001: 0.001 is divided by 50.
Practise more Data analysis, evidence and appraisal.
Free questions with an explanation for every one, and full timed PLAB 1 (GMC, international medical graduates) mock tests.
More Data analysis, evidence and appraisal questions
- Hospital length of stay in a sample is right-skewed. Which summary statistic is most appropriate to describe the central value?
- Which test is most appropriate for comparing the mean blood pressure before and after treatment in the same 30 patients, if the differences…
- Which test compares the proportion of smokers between two independent groups?
- A randomised trial analyses all patients in the groups to which they were originally assigned, including those who stopped treatment. What i…
- In a trial, the person allocating participants cannot know the next allocation in advance. Which bias does this concealment of allocation re…
- A funnel plot of studies in a meta-analysis is asymmetrical, with small negative studies missing. What does this suggest?