Differential analysis & tests / t-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.
The t-test compares two group means. Welch’s test (no equal-variance assumption) is the default, as recommended by most statistical texts; choose Student’s test only if you are confident the variances are equal.
Use a one-sided test only when the direction was fixed before the experiment. “First” means the first group in your data, or the first group you list under “Two groups to compare”.
The result table reports the mean difference with its confidence interval, t, degrees of freedom and P, plus Cohen’s d (pooled SD), Hedges’ g and an approximate CI for d, and Levene’s test for equal variances.
Batch mode: upload a feature × sample matrix and a sample sheet; every row (e.g. gene) is tested separately and P values are adjusted for multiple testing. Results are sorted by P and shown as a volcano plot of mean difference against −log10 P. Log-transform expression values first.
With very small or clearly skewed samples, also look at the rank-sum (Mann–Whitney) test.
Welch B. L. (1947) Biometrika 34:28–35; Student (1908) Biometrika 6:1–25. P values and confidence intervals match scipy.stats.ttest_ind. Cohen’s d = mean difference / pooled SD; Hedges’ g = d × (1 − 3/(4(n₁+n₂) − 9)); the CI for d uses the normal approximation of Hedges & Olkin (1985). Batch adjustment matches R p.adjust.
Up to 100,000 rows in long layout, 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.