A/B Test Calculator β statistical significance
Check whether your A/B test result is statistically significant: conversion rates, uplift, z-score, p-value and a plain-language verdict.
π Runs entirely in your browser. Your input and output are never sent to a server or stored β fully private.
Uses the pooled two-proportion z-test (two-tailed). A result is called significant at 95% when p < 0.05 (90%: p < 0.10, 99%: p < 0.01). Statistical significance is not a business guarantee β check the size of the uplift too. Click a result to copy.
About this tool
This A/B test calculator tells you whether a difference between two variants is real or just noise. Enter the visitors and conversions for A and B, and it computes each conversion rate, the relative uplift, a two-proportion z-test with its p-value, and a confidence interval for the difference. It states plainly whether the result is statistically significant at 95% (and shows the 90% and 99% bars too), so you can decide with evidence instead of a hunch. Everything is calculated locally in your browser.
Frequently asked questions
What does the p-value actually mean?
The p-value is the probability of seeing a difference at least this big if the two variants were actually identical. A small p (below 0.05) means such a gap would be unlikely by chance, so you call it significant. It is NOT the probability that B beats A, nor the size of the effect β a tiny, useless improvement can be significant with enough traffic. Read significance and uplift together: significant tells you the effect is real, uplift tells you whether it is worth shipping.
Why shouldn't I stop the test as soon as it goes green?
Because peeking repeatedly and stopping at the first significant moment massively inflates false positives β random noise will cross the 0.05 line temporarily surprisingly often. Decide your sample size in advance (a sample-size calculator helps), run the test to that size, and only then read the result. Also run for full business cycles: weekday-vs-weekend and payday effects can otherwise masquerade as a winning variant.
Does my traffic data leave my computer?
No. The z-test, p-value and confidence interval are all computed by JavaScript in your browser, so the visitor and conversion counts you enter are never uploaded or stored, and it works offline once loaded. That keeps commercial numbers private. This tool assumes each visitor is counted once and assigned independently; if the same users appear in both groups, the test's assumptions break.