A/B Test Calculator

Calculate statistical significance for your A/B tests to make data-driven decisions.

🧪

A/B Test Significance

Enter visitors and conversions for control and variant.

Control (Variant A) — Visitors

Control (Variant A) — Conversions

Variant B (Test) — Visitors

Variant B (Test) — Conversions

Statistical Significance

Relative Uplift

Summary

Visitors (A)

Conversions (A)

Conv. Rate (A)

Visitors (B)

Conversions (B)

Conv. Rate (B)

How Much Traffic Do You Need?

The sample size needed depends on your baseline conversion rate and the minimum effect you want to detect. Table below shows approximate per-variant sample sizes for 95% confidence and 80% power.

Baseline CVR	5% Uplift	10% Uplift	20% Uplift
1%	~310K / variant	~78K / variant	~20K / variant
2%	~155K / variant	~39K / variant	~10K / variant
5%	~62K / variant	~16K / variant	~4K / variant
10%	~31K / variant	~8K / variant	~2K / variant

A/B Testing Best Practices

Do:

Test one variable at a time
Wait for statistical significance
Run tests for full business cycles
Document tests and learnings

Don't:

Stop tests early when you see a winner
Change test parameters mid-experiment
Ignore external factors (seasonality)
Run multiple tests on the same audience