Key points at a glance
- Check two independent groups.
- Inspect ranks and distributions.
- Report without an automatic median claim.
Check that the question fits
The test compares two independent groups through the ranks of their observations. Values should support at least an ordinal ordering. Paired before/after measurements require a method for dependent data instead.
Inspect distributions before interpretation
Example: Groups A and B have the same median, but B has more very high values. A rank test can detect a distributional difference without justifying the blanket claim that “the medians differ”. A median interpretation needs additional shape assumptions.
Plan a traceable analysis
Define groups, outcome, exclusions and how ties will be handled before testing. Plot distributions and report group sizes plus sensible location and spread measures. A small p-value alone says nothing about practical importance.
Write the result precisely
Report U, p-value, group sizes and an effect size where appropriate for the software method. Explain which group tends to have higher ranks and what the distributions look like. Address multiple comparisons if you run many tests.
Final submission context
Formal details can feel like a separate writing task, but they matter just as much for a printed submission. Anything missing, misplaced or inconsistently formatted in the document will also appear in the bound copy.
Use this guide together with your cover page, table of contents, page numbers, source notes and appendices. Prepare the final PDF for printing and binding only after the complete file has been checked.
Practical check before PDF export
- Do headings, chapter structure and page numbers match?
- Are sources, figures and tables included completely?
- Are required elements such as declarations, appendices or the cover page included where required?
- Did you open and check the final PDF after exporting it?
Checklist
- Independence checked.
- Distributions plotted.
- U and p reported.
- Interpretation matched to shapes.
Common mistakes
- Testing paired measurements.
- Always claiming different medians.
- Reporting only a p-value.
Prepare the finished thesis for submission
Once the content and university requirements are checked, review your PDF and the available printing and binding options.
Review printing optionsRelated content
Explore related guidance on thesis structure, sources, formatting and final submission.
Frequently asked questions
Is it a test of medians?
Only with additional assumptions about distribution shape can it be interpreted that way.
Must data be normal?
No normality assumption like the classical t test is required.
What about three groups?
Choose a suitable multi-group procedure and analysis plan.