Key points at a glance
- Match the test to your design and hypothesis.
- Check independence, unusual observations and the relevant distribution.
- Report the difference, interval and effect size alongside the test.
Choose the right relationship between samples
Two separate groups call for an independent-samples approach. Repeated measurements on the same people are paired. Misclassifying the design changes the error estimate. Welch’s version can be appropriate for independent groups with unequal variances.
Check assumptions that matter here
Inspect independence, influential outliers and the distribution of observations or paired differences as relevant. Strong departures matter more in small samples. The test also needs a suitable measurement scale and a question set before looking at results.
Show the size and uncertainty
Report group means and spread, estimated difference, confidence interval, test statistic, degrees of freedom and p-value. Add an appropriate effect size. Statistical significance alone says little about practical importance.
Respect the study design
An observational difference does not establish a cause. Discuss selection, confounding and measurement. If you run many tests, explain your testing plan and how you handled the increased chance of false positives.
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 or pairing identified.
- Assumptions and test variant considered.
- Difference, interval and effect reported.
- Design limitations stated.
Common mistakes
- Treating repeated measures as separate groups.
- Reporting only a p-value.
- Inferring causation from an observational comparison.
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
When should I use a paired t-test?
When observations form meaningful pairs, such as before and after values from the same person.
What is Welch’s t-test?
A common independent-groups variant suitable when variances differ.
Is p < .05 enough to report?
No. Include magnitude, uncertainty and context.