Chi-squared test — MRCPsych Paper A MCQ

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

EasyEpidemiology and research methodsChi-squared testMRCPsych Paper A

In a parallel-group randomised trial, researchers compare the proportion of participants achieving remission after CBT with the proportion achieving remission after treatment as usual for panic disorder. The expected frequency in every cell is sufficiently large. Which statistical test is most appropriate?

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

Reveal the answer and explanation

Correct answer: C — Chi-squared test

The correct answer is C, the chi-squared test. Remission is a binary categorical outcome, and the study compares its proportions across two independent treatment groups. The stated adequate expected frequencies support use of Pearson's chi-squared test rather than an exact test. A paired t-test compares means from paired, approximately normally distributed continuous observations. The Wilcoxon signed-rank test is the non-parametric alternative for paired ordinal or continuous observations. Pearson correlation measures the strength of a linear association between two continuous variables. Bland–Altman analysis assesses agreement between two methods measuring the same continuous quantity; it does not compare remission proportions.

Reference: Sedgwick P. Statistical tests for independent groups: categorical data. BMJ. 2012;344:e344. https://www.bmj.com/content/bmj/344/bmj.e344.full.pdf