A researcher wants to measure the association between socioeconomic status graded as low, middle and high, and patient satisfaction scored on an ordinal five-point scale. Neither variable is normally distributed. The most appropriate test of association is:
- A Spearman rank correlation coefficient ✓
- B Pearson correlation coefficient
- C Chi-square test for trend
- D Paired t-test
Explanation
Spearman rank correlation is the non-parametric equivalent of Pearson correlation and is designed for ordinal data or for continuous data that violate normality, since it correlates the ranks rather than raw values. Pearson correlation requires interval scale variables with a bivariate normal distribution. B chi-square test assesses independence of categorical variables but does not quantify strength or direction of association on an ordinal scale.
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.