A/B Conversion Rate Comparison Calculator
Compare two conversion proportions, percentage-point difference, relative lift, a pooled z statistic and a clearly labelled normal-approximation interval.
YOUR CALCULATION
Result
—
Calculation steps
Work through one step at a time or reveal the complete calculation. The steps use your current inputs.
How to calculate
Calculate the observed proportions, pooled equal-rate test statistic and an unpooled Wald interval for their difference.
z=(pB−pA)/√[pooled p×(1−pooled p)×(1/nA+1/nB)]
Worked example
100/1000 conversions in A versus 130/1000 in B is a 3 percentage-point difference and 30% relative lift. The pooled equal-rate z statistic is about 2.103.
Assumptions and input details
Independent Bernoulli samples and a fixed, preselected analysis are assumed. The tool flags cells with fewer than 10 conversions or nonconversions; normal approximations, especially Wald intervals, may be unreliable there. The interval is not clipped to physical bounds. No probability of being the winner, sequential-test correction, causal claim or guaranteed uplift is reported.
References: NIST: equal-proportion normal-approximation test · NIST: difference-of-proportions intervals
Using this calculator
Can I enter my own problem?
Yes. Replace the example values with your own inputs. The result, calculation steps, tables and applicable diagrams update from those inputs. Blank or invalid values clear the result; example values are never silently substituted for missing inputs.
Are the results exact?
Results use floating-point arithmetic and displayed rounding. Read the formula, assumptions and any stated data precision before interpreting the result.
Is my input uploaded?
The calculation runs in your browser. No account, file upload or external AI service is required. Inputs are not saved between page reloads.
Estimate the sample count needed for a target margin of error for a mean or a proportion. Optionally apply a finite-population correction and round upward.
Calculate a two-sided confidence interval for a population mean from summary statistics. Choose Student t with sample SD or z with a known population SD.
Compare retained-revenue ROAS, contribution after ad spend and break-even ROAS using entered campaign counts, refunds, selling fees and unit costs.
Reserved advertising space.