A/B test calculator
Enter successes and total users for variants A and B. The result compares two independent proportions.
Variant conversion rates
Bars show the observed success share for variants A and B.
Variant data
| Variant | Successes | Sample size | Conversion |
|---|---|---|---|
| Fill in the fields above — the result is computed on this page. | |||
How do I use this page?
- Enter successes and totals for A and B.
- Choose the confidence level specified before analysis.
- Read the difference, interval and p value.
What this page does not do: The normal approximation is intended for independent groups and adequate counts. It does not handle paired data, repeated peeking or multiplicity across metrics.
Further reading
Theory — how does the A/B proportion test work?
The calculator compares successes and total users in variants A and B as a test of two independent proportions. It checks the hypothesis that the success probability is equal in both variants — the p-value describes how well the data fit this hypothesis, while the confidence interval shows the range of plausible differences B minus A. A smaller p-value does not mean a larger effect, since it also depends on sample size; the absolute difference between variants shows the effect size.
Frequently asked questions
Does a smaller p value mean a larger effect?
Can I stop as soon as p falls below 0.05?
See also
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.
Adjusted R-squared calculator
Convert R² to adjusted R² using the number of observations and predictors in a regression model.