A/B Test Calculator — Mathilda's Lab

Statistical significance, Bayesian probability, and sample size estimation. Know when your test is done.

📊

Enter your data

Fill in visitors and conversions above

—

p-value

—

z-score

—

relative uplift

—

statistical power

Control

4.50%

Variant

6.20%

Chance that each variant is the winner (Monte Carlo, 100k simulations)

30%

70%

Control (A) wins Variant (B) wins

—

expected lift

—

risk of choosing B

To detect the observed difference at your chosen confidence level with 80% power:

—

visitors per variant