CRO Tool
A/B Test Statistical Significance Calculator
Enter your visitors and conversions. We'll instantly calculate the uplift, p-value and whether the difference is statistically significant.
Variant A (control)
Variant B (challenger)
95% is the standard in CRO. Choose 99% for extra certainty on high-stake changes.
Used to estimate how much longer the test needs to run.
Significant
Variant B wins
The 0.80% difference in conversion rate is statistically significant at 95% confidence.
What does significance mean?
Statistical significance indicates how likely it is that the difference between A and B occurred by chance. At 95% confidence, there's only a 5% chance the difference is due to chance.
Which test is used?
We use a two-sided z-test for two proportions with pooled standard error. The confidence interval of the difference is based on the unpooled SE.
When should you stop testing?
Decide in advance how many visitors you need and let the test run for at least 1 full business cycle (often 1-2 weeks). Don't stop early just because a result looks 'good'.
Need help with your CRO strategy?
We help you set up a structured testing programme, from hypothesis to implementation. More results from the same visitors.