Skip to Main Content
The Library

MASH : Maths and Stats Help

Mann-Whitney U-Test

Introduction

A Mann-Whitney U-Test compares the means between two unrelated groups, such as comparing the difference in heights between Cats and Yorkshire Terriers.

It is considered a non-parametric test and therefore is suitable for non-parametric data. To check if your data is parametric, please check our dedicated guide: Parametric or Not Guide (PDF)

If your data is non-parametric you should consider using an Independent-Samples t-Test

 

Test Procedure

  1. Click Analyze > Nonparametric Tests> Legacy Dialogs > 2 Independent Samples

  2. Within the Two-Independent-Samples box, select the test variable or dependent variable you are analysing and move it to the ‘Test Variable List’ box. Then move your independent/grouping variable into the “Grouping Variable” box.

  3. Select Define Groups and specify the groups you are going test. In this example I am testing Cats which are labelled 1 against Yorkshire Terroirs which are labelled 2, therefore my groups are numbered 1 and 2.

  4. Select Options and click Descriptive Statistics

  5. Select Continue à OK

 

Results

 

SPSS will generate three tables, for this test we need two, the Descriptive Statistics and the Test Statistics:

Descriptive Statistics

This table shows a selection of descriptive statistics: the sample size of each group (N), the mean of each group (Mean), and the standard deviation of each group (Std. Deviation), best practice is to report them all.

Test Statistics

This table shows the specific test results including the Mann-Whitney U statistic (U), the Wilcoxon Statistic (W), the z-score (Z) and two different p-values / significance values. For the vast majority of applications, you will need to report the Asymp. Sig (2-tailed) version of the p-value.

Reporting the Results in APA Formatting

Heights of Cats and Yorkshire Terriers were compared. On average the Yorkshire Terriers (Mdn = 29.27) were taller than the Cats (Mdn = 28.00) however a Mann-Whitney U test indicated that this difference was not statistically significant, U(NCats=11, NTerriers=11)=35.5, z=1.67, p=.094