A/B test sample size calculator

Sample size is the number of visitors each variant needs before an A/B test can tell a real lift apart from random noise. It grows when your baseline conversion rate is low, when the lift you want to detect is small, and when you demand higher confidence or power. This calculator uses the standard two-proportion approximation with variance taken at the baseline rate:

Here p is the baseline conversion rate, MDE is the relative lift you want to detect, and z_α and z_β come from your chosen confidence level and statistical power. The result is per variant, so a two-variant test needs about twice that many visitors in total.

Use your real baseline conversion rate from analytics rather than an industry average. Set the minimum detectable effect to the smallest lift that would actually change a business decision: chasing a 1% lift on low traffic can demand millions of visitors, so most stores target larger, more meaningful swings. Keep confidence at 95% and power at 80% unless you have a specific reason to change them, since those are the conventional defaults for commercial A/B testing.