A/B Test Sample Size Calculator

Before you launch an experiment, find out how much traffic you need to trust the result.

Baseline conversion rate (%)
Minimum detectable effect (% relative)
Statistical significance
Statistical power
Sample size needed per variant
8,158
16,316 visitors total (A + B), to detect a lift from 5% to 6.00% at 95% significance and 80% power.

Uses a two-sided two-proportion test. Results are an estimate for planning — final power depends on your actual variance and traffic.

Why sample size matters

Calling a test too early is the most common experimentation mistake. Without enough samples, a random swing looks like a winner. This calculator estimates the visitors per variant needed to detect your target lift at a given significance and power.

The inputs, explained

  • Baseline conversion rate — your current rate for the metric you're testing.
  • Minimum detectable effect — the smallest relative improvement worth detecting.
  • Significance — the chance of a false positive you'll accept (95% = 5%).
  • Power — the chance of detecting a real effect (80% is standard).

Learn the fundamentals in our conversion rate glossary entry.