Key points at a glance
- Check a 2×2 independent design.
- Inspect expected cell counts.
- Report proportions and effect with p.
Check the question and design
Fisher’s exact test examines association between two categorical variables in a 2×2 table. Observations must be appropriately independent. Total sample size alone is not the whole decision: small expected cell counts can make a chi-square approximation unreliable.
Inspect cells, not only total n
Example: Twenty-four people are classified by study mode and support for a policy; one of four cells contains only two observations. Show all counts and proportions. Describe whether the groups comprise independent individuals.
Document the test choice
Decide whether a one- or two-sided alternative fits the question specified in advance. Use the exact procedure when design and assumptions support it. Paired yes/no observations or larger tables may need another method.
Interpret at the scale of the data
Report cell values, p-value and, where useful, an odds ratio with uncertainty. Association is not proof of causation. Small datasets can yield imprecise estimates; do not hide this behind one p-value.
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.
- Cell counts inspected.
- Alternative specified.
- Proportions and uncertainty shown.
Common mistakes
- Looking only at total n.
- Treating paired records as independent.
- Reporting p as the effect size.
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 Fisher rather than chi-square?
When the 2×2 question fits and small expected cells undermine the approximation.
Can I use it for every table?
Check table size, design and implementation; not every question is an independent 2×2 comparison.
Should I report an odds ratio?
When meaningful, it helps describe direction and size.