Fisher's Exact Test

Fisher's exact test is a test of association between two categorical variables in a contingency table that calculates an exact p-value from the hypergeometric distribution rather than a large-sample approximation.

피셔의 정확검정은 분할표에서 두 범주형 변수의 연관성을 검정하며, 대표본 근사 대신 초기하분포로부터 정확한 p값을 계산하는 방법입니다.

How do I test the association between two categorical variables when my sample is small?

표본이 작을 때 두 범주형 변수 사이의 연관성은 어떻게 검정하나요?

Fisher's exact test assesses whether two categorical variables are associated by computing the exact probability of the observed table given its row and column totals. It is the standard choice for 2x2 tables with small samples or expected cell counts below 5, where the chi-square approximation is unreliable.

When to use Fisher's Exact Test

• A 2x2 table comparing a binary outcome between two groups with a small sample
• Contingency tables where one or more expected cell counts are below 5
• Rare outcomes, such as adverse events, cross-tabulated by group

When to use something else

• Large samples with adequate expected counts: use the chi-square test of independence
• Paired or matched binary data: use McNemar's test

Assumptions and requirements

• Independent observations, each counted in exactly one cell
• Categorical variables with mutually exclusive categories
• Inference is conditional on the observed row and column totals

What the analysis reports

• Contingency table of observed counts
• Exact p-value (one- or two-sided)
• Odds ratio with confidence interval for 2x2 tables
• Row or column percentages

How to report it

Fisher's exact test showed a significant association between [variable 1] and [variable 2], p = [value], OR = [value], 95% CI [[value], [value]].

Related methods

• Chi-Square Test of Independence
• McNemar's Test
• Barnard's Exact Test

Run Fisher's Exact Test on Quorant