Free tool
Your test is finished — but did the variant actually win? Enter the visitors and conversions for each version and see the p-value, the confidence interval and a plain-English verdict. Everything is calculated in your browser as you type.
The variant beats the control — the difference is statistically significant.
p = 0.0283 at 95% confidence
FAQ
It means the difference you measured is unlikely to be a fluke. A p-value of 0.03 says that if the two versions were really identical, you would see a gap this big (or bigger) about 3% of the time. It is evidence that something changed — not proof, and not a measure of how big the change is.
The convention is p below 0.05, which matches 95% confidence. Raise the bar to 99% when the change is expensive to ship or hard to reverse, and accept 90% for low-risk copy tweaks where being roughly right quickly is worth more than being certain slowly.
No. Checking repeatedly and stopping at the first green result — peeking — inflates false positives badly. Decide the sample size before you launch, run to it, then read the result once. The sample size calculator gives you that number.
No. The whole test runs in your browser with plain JavaScript. Nothing you type is uploaded, logged or stored, and the page works offline once loaded.
Related
A p-value tells you that something changed. PulsePanda's session replay, heatmaps and funnels tell you what people actually did.
Start for free