Wilcoxon-Mann-Whitney Test

Introduction

The Mann-Whitney U test (Wilcoxon Rank Sum Test or Mann-Whitney test ) is a non parametric alternative of independent students t test and it is used to compare differences between two independent groups when the dependent variable is either ordinal or continuous, but not normally distributed.

Example: Data

Consider the following data from a randomized study having two treatment groups – Treatment A and Treatment B. Test_value was used to assess the significance diference between treatment groups at each visit1 and visit2.

Hypothesis are: Null hypothesis H0 = test_value not significant between treatments vs Alternative hypothesis H1 = test_value not significant between treatments

95 % Hodges-Lehman CI for diffrence in test_value beetween tretment A and treatment B also estimated.

SAS Code

proc npar1way data=ts wilcoxon alpha=0.05 HL ; 
  class Treatment by visit;
  var test_value ;
run;

• Two sided p value (Two-Sided Pr >|Z|) from t Approximation for both visit 1 and visit 2 are <0.05, which can be interpret as in both vists test_value is not significant at 5% level of significance. • 95 % Hodge Lehman Estimator of CI for diffrence in test value beetween treatment A and treatment B for visit1 visit2 are (-0.1290, 0.1900) and (-0.1480, 0.1070) respectively.