A researcher wants to compare pain scores measured on an ordinal scale (0-10) before and after an intervention in 15 patients. The differences between pre and post scores are not normally distributed. Which test is most appropriate?
- A Paired t-test
- B Wilcoxon signed-rank test ✓
- C Mann-Whitney U test
- D Repeated measures ANOVA
Correct answer: B. Wilcoxon signed-rank test
Explanation
Wilcoxon signed-rank test is the non-parametric alternative to the paired t-test, used for paired data when differences are not normally distributed or when data are ordinal. Mann-Whitney U test is for two independent groups. Paired t-test requires normally distributed differences. Repeated measures ANOVA is parametric and for multiple time points.
Reference: Methods in Biostatistics, 7th ed.
High-yield for: NEET PGINI-CETNExTFMGEUSMLEPLABMRCP
Written and medically reviewed by the StethoPrep medical team.