# A/B test significance calculator

Check whether variant B really converts differently from A, and how many visitors you need.

## How it works

A two-proportion z-test compares the conversion rates, and the p-value is the chance of a gap this big if there were no real difference.

The sample size is what each variant needs to detect the smallest lift you care about, at your confidence and 80% power.

```
z = (p_B − p_A) ÷ √(p(1 − p)(1/n_A + 1/n_B))
```

## Questions

### Can I stop as soon as it’s significant?

Stopping early inflates false positives. Decide the sample size first and stop when you reach it.

### Why do I need so many visitors?

Small lifts on low conversion rates are hard to tell from noise.

## Related tools

- [Speed vs revenue calculator](https://powertraces.com/tools/speed-vs-revenue)
- [Observability ROI calculator](https://powertraces.com/tools/observability-roi)
- [SLA credit calculator](https://powertraces.com/tools/sla-credits)
- [Funnel drop-off calculator](https://powertraces.com/tools/funnel-drop-off)

[All tools](https://powertraces.com/tools)