Work out how long an A/B test must run to reach its required sample size.
Duration follows directly from required sample size and traffic. Tests should always run in whole weeks because conversion behaviour differs systematically between weekdays and weekends. Adding variants divides traffic and extends duration proportionally, which is why multivariate tests so often prove impractical.
A/B Test Duration
Duration = required sample per variant ÷ (daily visitors × allocation ÷ variants)
Duration = required sample per variant ÷ (daily visitors × allocation ÷ variants) Duration follows directly from required sample size and traffic. Tests should always run in whole weeks because conversion behaviour differs systematically between weekdays and weekends.
Adding variants divides traffic and extends duration proportionally, which is why multivariate tests so often prove impractical.
This calculator takes 4 inputs: Sample size needed per variant, Daily visitors, Share of traffic in the test, Number of variants. The pre-filled defaults are a realistic starting point — replace them with figures from your own environment for a result you can act on.