A/B Test Size Calculator
How many visitors and days does my test need?
Also known as: A/B test sample size calculator
Test plan
Visitors needed per version
- Total visitors
- 42,218
- Days to finish
- 15
- Target conversion rate
- 2.4%
- Conversions per version
- 422
At your daily traffic, split evenly.
Expected at the current rate.
Save this result
Keep it in your workspace with a note. Free accounts keep 5 results; Pro keeps them all.
How it works
How does the A/B Test Size Calculator work?
Sample size per version comes from the two-proportion z-test: it depends on your baseline conversion rate, the smallest relative lift you want to detect, the confidence level and the statistical power. Testing more than two versions tightens the confidence level for each comparison (Bonferroni).
- n = (z₁₋α/2·√(2p̄(1−p̄)) + z₁₋β·√(p₁(1−p₁)+p₂(1−p₂)))² ÷ (p₂−p₁)², where p₂ = p₁ × (1 + lift).
- With k versions, each of the k−1 comparisons with control uses α ÷ (k−1).
- Days = total visitors needed ÷ daily visitors, assuming an even split.
- Run whole weeks where you can, so weekday and weekend behaviour are both in the sample.
Worked example
2% baseline, 20% relative lift, 95% confidence, 80% power, two versions: 21,109 visitors per version, 42,218 in all. At 3,000 visitors a day that's 15 days, with about 422 conversions per version.
Limits
Assumes visitors are independent and the split is even. Peeking at results and stopping early invalidates the plan.
Related tools
Private by default
Your inputs stay in this browser.
This free calculation runs locally and is a planning aid, not financial, tax or legal advice. Nothing you type leaves this page unless you choose to save it.