Sample Size Calculator

n = z² × 0.25 ÷ margin², where z is the z-score for your chosen confidence level (1.645 for 90%, 1.96 for 95%, 2.576 for 99%) and margin is your acceptable margin of error as a decimal.

0.25 represents the worst-case assumption of a 50% true conversion/response rate, which produces the largest (most conservative) required sample size. This calculator doesn't let you plug in your own expected rate — if your actual rate is far from 50%, the true required sample size could be smaller than this estimate.

95% confidence with a 5% margin of error is the common default for most A/B tests and surveys; tighten the margin (e.g. to 2-3%) if you need more precision, which will increase the required sample size.

The formula is general-purpose for estimating proportions from a sample — it applies equally to A/B test conversion rates and survey response percentages.