A researcher computes a Mann-Whitney U test instead of an independent-samples t-test for comparing pain scores between two treatment groups. The most appropriate reason for this choice is:
- A Pain scores are measured on an ordinal scale and are not normally distributed ✓
- B The sample sizes in both groups are unequal
- C Both groups have the same variance
- D The study is a randomized controlled trial
Correct answer: A. Pain scores are measured on an ordinal scale and are not normally distributed
Explanation
The Mann-Whitney U test is the non-parametric equivalent of the independent-samples t-test, appropriate when the outcome is on an ordinal scale or when the normality assumption is violated (non-normally distributed data, particularly with small samples). Parametric tests like the t-test require at least approximate normality. Unequal sample sizes or equal variance do not necessitate non-parametric testing; Welch's t-test handles unequal variances. Study design (RCT) does not determine the choice of statistical test — the measurement scale and distribution do.
Reference: Park's Textbook of Preventive and Social Medicine, 27th ed.
High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP
Written and medically reviewed by the StethoPrep medical team.