Differential analysis & tests / Fisher's exact test
Your data stays in your browser: files are read and processed on your device, never uploaded to any server, and cleared when you close the page. Free, no sign-in.
Fisher’s exact test is for 2×2 tables: the P value is computed exactly from the hypergeometric distribution, with no large-sample approximation. Prefer it to the chi-square test when counts are small (expected < 5).
Cells are a b / c d (first row, second row); an odds ratio above 1 means the first row has higher odds of falling in the first column. Categories are sorted alphabetically unless you set “Category order” (row variable; column variable).
Two odds ratios are given: the conditional maximum-likelihood estimate with its exact CI (as in standard Fisher-test software), and the sample odds ratio ad/bc with the Woolf (log-normal) interval.
Batch mode: one 2×2 table per row (e.g. carrier counts for many genes or variants); every row is tested, P values are adjusted, and the chart shows log2 odds ratio against −log10 P.
Fisher R. A. (1922) J R Stat Soc 85:87–94; Cornfield J. (1956) (exact interval); Woolf B. (1955) Ann Hum Genet 19:251–253. P matches scipy.stats.fisher_exact; odds ratios and intervals match scipy.stats.contingency.odds_ratio (conditional / sample).
Up to 200,000 rows of raw data or 200,000 tables in batch mode.
Send us your data and research question and you will receive a written plan within 1 working day: analysis steps, parameter rationale, deliverables and timeline. Quoted per project.