How it works
Compute conversion rates, their difference and a pooled two-proportion z statistic. Approximate two-sided p with the standard normal tail; report an unpooled 95% difference interval.
Input definitions
- Group A visitors
- Enter the value in the labeled unit.
- Group A conversions
- Enter the value in the labeled unit.
- Group B visitors
- Enter the value in the labeled unit.
- Group B conversions
- Enter the value in the labeled unit.
A worked example
- Group A visitors
- 1000
- Group A conversions
- 100
- Group B visitors
- 1000
- Group B conversions
- 120
Assumptions & limits
Entered-data planning worksheet. No legal, payroll, tax-filing or accounting certification.
Sources & review
Maintained by AnsRio. Methods and examples use automated checks; this does not imply independent professional certification.
Method updated 2026-10-17. Content checked against the stated method and examples. Our verification approach.
Common questions
Does a small p-value prove that a campaign will win in production?
No. It addresses a statistical model, not effect importance, experiment quality or future performance. Repeated testing and biased assignment can invalidate interpretation.
How does A/B conversion difference and z-test work?
Compute conversion rates, their difference and a pooled two-proportion z statistic. Approximate two-sided p with the standard normal tail; report an unpooled 95% difference interval.
What are the limits of A/B conversion difference and z-test?
Entered-data planning worksheet. No legal, payroll, tax-filing or accounting certification.