Compare two groups? Find what drives an outcome? Spot a trend? The question decides the statistics — get this wrong and everything downstream is wrong too.
That is the actual report this analysis produces — not a mock-up. Every analysis on this page delivers the same shape of output on your own data.
Every analysis classified under this question.
Can I stop this experiment early? Sequential testing with always-valid inference so peeking does not inflate false positives.
Library tool, v2: each variant against a control on a conversion rate or a mean, Holm-adjusted, with a sample ratio check, power and th
Do my groups differ once I adjust for a covariate?
Library tool, v2: two categorical columns as one table. The counts, the rate of one outcome level per group with Wilson 95% intervals,
Are these two things practically the SAME within a margin?
Did the change move the metric?
Standard-library analysis: does a numeric outcome differ between groups? One deck runs the whole toolkit — Welch and Student t-tests fo
Library tool, v2: Bonferroni, Holm and Benjamini-Hochberg corrections of a set of raw p-values; eight objects into run_objects (summary
Did things change before vs after?
Library tool, v2: two measurements of the same subjects. Numeric pairs: paired t with its interval, Wilcoxon signed-rank with the Hodge
Is the comparison fair once groups are matched?
Did the same subjects change across three or more conditions?
Tell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.