Paired t-test — MRCPsych Paper A MCQ

Instant feedback + full explanation. One question, done properly.

EasyEpidemiology and research methodsPaired t-testMRCPsych Paper A

A study measures Hamilton Depression Rating Scale scores in the same patients before and after an intervention. The within-patient differences are approximately normally distributed. Which statistical test is most appropriate for comparing the mean scores before and after the intervention?

Educational content. Not a substitute for clinical judgement or local policy.

Reveal the answer and explanation

Correct answer: D — Paired t-test

The correct answer is D, the paired t-test. The outcome is quantitative, each patient contributes two linked measurements, and the within-patient differences are approximately normally distributed. The paired t-test evaluates whether the mean of these differences differs from zero while accounting for the dependence between observations from the same person. An unpaired t-test is intended for two independent groups and would disregard the pairing. Chi-squared and Fisher exact tests analyse categorical frequency data, not mean continuous scores. The log-rank test compares time-to-event distributions and requires survival or censoring data.

Reference: BMJ. Statistics at Square One: 7. The t tests, section 'Difference between means of paired samples (paired t test)', 2020. https://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/7-t-tests