A/B test significance calculator
A difference is significant at 95% when its p-value is below 0.05: if A and B truly converted the same, a gap this large would show up less than 5% of the time. This page runs a two-sided, two-proportion z-test on the visitors and conversions you enter.
Free, no sign-up. Everything runs in your browser.
Exactly what this page computes
rate A = conversions A / visitors A, rate B = conversions B / visitors B pooled rate p = (conversions A + conversions B) / (visitors A + visitors B) standard error = √( p × (1 − p) × (1 / visitors A + 1 / visitors B) ) z = (rate B − rate A) / standard error p-value = 2 × (1 − Φ(|z|)), significant when p-value < 1 − confidence
How to read it
Can I stop the test as soon as it turns significant?+
Better not. Checking again and again and stopping at the first significant reading makes false winners far more likely. Decide the sample size before you start and read the result once you reach it.
Why does it warn about too little data?+
The z-test leans on a normal approximation that needs at least 5 conversions and 5 non-conversions in each variant. Below that, collect more data before reading the result.
Does significant mean the uplift is that big?+
No. It means the difference is unlikely to be zero. The true uplift can be smaller or larger than the one measured, especially on small samples.
Let the audit run this on your whole account.
SuperGen checks your Google Ads around the clock against a published catalogue, shows the method behind every figure, and hands you the fix to apply in one click. Meta is coming soon.