A/B Test Significance Calculator
Two-proportion z-test with p-value and verdict.
The formula behind it
z = (p̂B − p̂A) ÷ √[ p̂(1−p̂) × (1/nA + 1/nB) ] • p-value = 2 × (1 − Φ(|z|))- p̂A, p̂B
- observed conversion rates of the two variants
- p̂
- pooled rate across both groups
The standard two-proportion z-test asks whether the difference you saw exceeds what sampling noise typically produces. The pooled standard error assumes the null hypothesis (no difference) — the correct test for 'is there any difference?'. The verdict is at your 0.05 threshold: 'not significant' means not proven, not proven equal.
How to use this calculator
- 1
Enter visitors and conversions for variant A.
- 2
Enter visitors and conversions for variant B.
- 3
Read the rates, the z-score, the p-value and the verdict.
Worked examples
A real winner
4% vs 6% with 1,000 each → z ≈ 2.05, p ≈ 0.040 — significant at 0.05.
Same rates, smaller sample
8% vs 14% with 500 each → still significant; the same experiment at 100 visitors would not be.