Statistical Significance Calculator
Check whether your A/B test result is real or just noise. Enter the numbers and get confidence, p-value, and a verdict.
Stop calculating. Start testing.
Drop in your site and Dalton finds the experiment, sizes it, builds it, and ships the winner for you.
How to check statistical significance
Significance answers one question: is the gap between your variant and control real, or could it be luck? The calculator runs a two-proportion z-test on your visitors and conversions and returns a confidence level and a p-value. If confidence clears your threshold, usually 95 percent, the result is significant and you can call it.
Significance is not the whole story
A significant result still needs enough data behind it. If your test is underpowered, you can hit significance by chance, or miss a real winner entirely. Plan the test first with the sample size calculator, then let it run to that target instead of stopping the moment it looks good.
Frequently asked questions
How do I know if my A/B test is statistically significant?
Enter the visitors and conversions for your control and your variant. The calculator runs a two-proportion z-test and tells you the confidence level, the p-value, and whether the result clears your threshold.
What does statistical significance mean?
It is the confidence that the difference between your variant and control is real rather than random chance. 95 percent confidence means there is a 5 percent chance you would see a result this extreme if there were truly no difference.
What is a p-value?
The probability of seeing a result at least this extreme if the variant and control actually performed the same. A p-value below 0.05 corresponds to 95 percent confidence and is the usual bar for calling a winner.
What significance level should I use?
95 percent is standard for most conversion tests. Use 99 percent when a wrong call is expensive, and 90 percent only for low-stakes early reads.
My result is not significant yet. What now?
Keep the test running until it reaches significance or you hit the sample size you planned. Stopping the moment it looks significant, known as peeking, inflates false positives. Size the test first with the sample size calculator.