Differential analysis & tests / One-way ANOVA with post-hoc
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.
One-way ANOVA tests whether all group means are equal. The classic F-test assumes equal variances; if Levene’s test gives P < 0.05, choose Welch’s ANOVA.
After a significant overall test, Tukey’s HSD compares every pair while controlling the family-wise error rate; the table gives mean differences, confidence intervals and adjusted P values.
Letters: the group with the highest mean gets “a”; two groups that share no letter differ significantly (at your α), groups sharing a letter do not.
Effect size η² = between-group SS / total SS; ω² is a less biased estimate and more reliable for small samples.
Batch mode: upload a feature × sample matrix and a sample sheet; each row gets its own ANOVA, P values are adjusted for multiple testing, and the chart shows the P-value distribution.
Fisher R. A. (1925); Welch B. L. (1951) Biometrika 38:330–336; Tukey J. W. (1949) Biometrics 5:99–114 (Tukey–Kramer for unequal sizes); letters by Piepho H.-P. (2004) J Comput Graph Stat 13:456–466. F and P match scipy.stats.f_oneway / statsmodels anova_oneway; Tukey results match scipy.stats.tukey_hsd.
Up to 100,000 rows, or 100,000 features 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.