Which test is most appropriate for comparing pain scores (ranked 1 to 10) between two independent groups when the data are clearly not normally distributed?
Free Applied Statistics in Healthcare practice question on Non-parametric tests and chi-square for BSN and Post-RN nursing students. Choose your answer, then open the answer and the explanation.
APaired-samples t-test
BPearson correlation test
CMann-Whitney U test
DIndependent-samples t-test
Show answer and explanation
✓ Correct answerC. Mann-Whitney U test
Explanation
Non-parametric tests are used when data do not meet the assumptions of parametric tests, especially normality, or when the outcome is ordinal or ranked. They work on ranks or signs rather than means and standard deviations, so they suit small samples and skewed or ranked data such as pain scores. The Mann-Whitney U test is the non-parametric alternative to the independent-samples t-test for two unrelated groups.
Why each option is right or wrong
✗A. Paired-samples t-test — It compares two measurements taken in the same person, not two separate groups of patients.
✗B. Pearson correlation test — It measures the strength of a linear relationship between two continuous variables rather than comparing group locations.
✓C. Mann-Whitney U test — A rank-based test for two independent groups, used when the outcome is ordinal or not normally distributed.
✗D. Independent-samples t-test — It assumes normally distributed data and compares means of two unrelated groups, so ranked pain scores violate its assumptions.
Situation
Parametric choice
Non-parametric alternative
Two independent groups
Independent-samples t-test
Mann-Whitney U test
Two related measurements
Paired-samples t-test
Wilcoxon signed-rank test
Three or more independent groups
One-way ANOVA
Kruskal-Wallis test
Three or more related groups
Repeated-measures ANOVA
Friedman test
EXAM HINT Ranked or skewed data: think Mann-Whitney for two separate groups, Wilcoxon for the same group twice.
اردو وضاحت
Non-parametric test کیا ہے؟
Non-parametric test اُس وقت استعمال ہوتا ہے جب ڈیٹا نارمل distribution نہ ہو یا outcome ranked ہو، جیسے pain score۔ یہ اوسط کی بجائے ranks پر کام کرتا ہے، اس لیے چھوٹے sample اور skewed ڈیٹا میں بھی چل جاتا ہے۔
دو الگ گروپس کے ranked ڈیٹا کے لیے کون سا test ٹھیک ہے؟
جب pain score جیسا ranked ڈیٹا ہو اور دو الگ الگ مریضوں کے گروپس کا موازنہ کرنا ہو تو Mann-Whitney U test صحیح انتخاب ہے، کیونکہ یہ ranks پر چلتا ہے اور normality کی شرط نہیں رکھتا۔ t-test mean مانگتا ہے، اور pain score میں mean کا مطلب زیادہ قابلِ اعتماد نہیں ہوتا۔
Key terms
normally distributed — Data shaped like a bell curve with most values near the middle. (ایسا ڈیٹا جو گھنٹی کی شکل کا ہو اور زیادہ تر اقدار درمیان میں ہوں۔)