Which test compares two independent groups when the data are ordinal and normality cannot be assumed?
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 t-test
BPearson correlation
CMann-Whitney U test
DOne-way ANOVA
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, such as normality or interval-level measurement. The Mann-Whitney U test compares the ranks of two independent groups, so it suits ordinal data or skewed continuous data from separate samples.
Why each option is right or wrong
✗A. Paired t-test — Requires normally distributed interval data and compares paired measurements from the same subjects.
✗B. Pearson correlation — Measures the strength of a linear relationship between two continuous variables rather than comparing groups.
✓C. Mann-Whitney U test — Compares ranks of two independent groups, so it fits ordinal data that are not normally distributed.
✗D. One-way ANOVA — Compares means of three or more groups and assumes normal distribution and equal variances.
Test
Data type
Groups compared
Distribution assumption
Mann-Whitney U
Ordinal / non-normal
Two independent
None (rank-based)
Paired t-test
Interval
Two paired measurements
Normal differences
One-way ANOVA
Interval
Three or more independent
Normal, equal variances
Pearson correlation
Interval
Two continuous variables
Bivariate normal
EXAM HINT Mann-Whitney = 'Mann to Mann' two separate groups, ranked not measured.
اردو وضاحت
Non-parametric test کیا ہوتا ہے؟
Non-parametric test اُس وقت لگاتے ہیں جب data normal distribution follow نہ کرے یا صرف ranking کی صورت میں ہو۔ یہ test mean کی بجائے ranks پر کام کرتا ہے، اسی لیے ordinal data کے لیے بہتر رہتا ہے۔
دو الگ groups کے ordinal data پر کون سا test لگائیں؟
جب دو الگ الگ groups ہوں اور data ordinal ہو یا normal نہ ہو تو Mann-Whitney U test صحیح انتخاب ہے کیونکہ یہ دونوں groups کے ranks کا آپس میں موازنہ کرتا ہے۔ Paired t-test اسی group کے دو بار لیے گئے readings کے لیے ہے، اس لیے یہاں مناسب نہیں۔