Draft: This page has not been reviewed by a statistician yet. Use it as a starting point and check important choices with a statistician.

Fisher's exact test

Compares the proportion of patients with a yes/no outcome between independent groups when some groups have very few events.

Clinical example

A rare complication compared between two surgical techniques, where only a handful of patients in either group had it.

When to use it

The outcome is yes or no, one per patient.
You compare independent groups.
Fewer than about 5 patients are expected in some cell of the table.

Assumptions to check

Independent observations

Each patient appears in the table once.

What to report

Number and percentage with the outcome in each group
Odds ratio with 95% CI
The exact p-value, not just "p < 0.05"

Common mistakes

Report the effect, not just the p-value

Give the estimate (difference, ratio) with its 95% confidence interval and the exact p-value.

Alternatives

If your situation is…	Use
About 5 or more expected in every cell	Chi-square test

In your software

R

# R
tab <- table(trial$technique, trial$complication)
fisher.test(tab)

SPSS

CROSSTABS
  /TABLES=technique BY complication
  /STATISTICS=CHISQ RISK
  /CELLS=COUNT EXPECTED ROW.