统计与概率
即时、私密且免费
Fishers Exact Test Calculator.
Calculate this statistic instantly with validated formulas.
输入数值
输入时结果会更新。
Use Cases
Analyze small-sample contingency tables
Use this calculator when you have a 2x2 table with small expected counts, where the chi-square test may not be valid. It provides an exact p-value for testing independence.
Example: Compare treatment success rates in a small clinical trial: 4 successes vs 1 failure in treatment group, 1 success vs 5 failures in control group.
Validate research findings
Quickly verify the statistical significance of your observed association without manual computation, ensuring accuracy in your analysis.
Example: Check if a genetic marker is associated with a disease in a small case-control study.
Frequently Asked Questions
- What is Fisher's exact test?
- Fisher's exact test is a statistical significance test used for 2x2 contingency tables when sample sizes are small. It calculates the exact probability of observing the table given the marginal totals, under the null hypothesis of independence.
- How do I enter the values?
- Enter the four cell counts of your 2x2 table as comma or space separated numbers. For example, '10 5 3 8' or '10,5,3,8'. The order should be top-left, top-right, bottom-left, bottom-right.
- What does the p-value tell me?
- The p-value indicates the probability of obtaining results at least as extreme as the observed data, assuming the null hypothesis is true. A small p-value (typically < 0.05) suggests evidence against the null hypothesis.
Tips & Common Mistakes
Tips
- Ensure your table is 2x2; the calculator expects exactly four numbers.
- Use whole numbers for counts; decimals are not appropriate for contingency tables.
- Double-check the order of your values to match the standard layout: row1 col1, row1 col2, row2 col1, row2 col2.
- For one-tailed tests, interpret the p-value accordingly; this calculator provides the two-tailed p-value.
Common Mistakes to Avoid
- Entering more than four numbers or missing a number, which will cause an error.
- Using percentages or proportions instead of raw counts.
- Misinterpreting the p-value as the probability that the null hypothesis is true.
Last updated: August 13, 2026