A/B Test Sample-Size Calculator

Enter your current conversion rate and the minimum improvement you want to detect. The calculator returns the number of visitors you need per variant to reach statistical significance.

How to Use This

1. Baseline conversion rate — your current conversion rate for the page or flow you are testing. Check your analytics for the last 30 days.
2. Minimum detectable effect (MDE) — the smallest relative improvement you care about. A 20% MDE on a 3% baseline means you want to detect a move from 3.0% to 3.6%.
3. Confidence level — 95% is standard. Use 90% for exploratory tests; 99% for high-stakes changes.
4. Statistical power — 80% is the most common default. 90% reduces the chance of missing a real effect but requires more traffic.

The result is the number of visitors per variant. For a standard A/B test (two variants), double it to get total traffic required. Divide by your daily traffic to estimate how many days the test needs to run.

Rules of thumb

• Always run a test for at least one full business cycle (usually 7 days) even if you hit the sample size sooner.
• Do not peek at results and stop early—that inflates false-positive rates. Decide your stop criteria before launch.
• If the required sample size is larger than 4 weeks of traffic, either increase the MDE (look for bigger wins) or test on a higher-traffic page.