Worked Walkthrough: Size A Conversion Test
Work through sample-size planning for a two-proportion A/B test.
Can a one-week test with 40,000 eligible visitors detect signup completion moving from 10% to 11%? Baseline rate + MDE + alpha + power -> required sample per arm The common trap is to treat "40,000 visitors" as automatically large without checking whether it can detect the specific one-point lift. Baseline Start with the current conversion rate: p0 = 10%. Baseline determines expected variance. A proportion near 50% is noisier than one near 0% or 100%, but even a 10% rate needs real sample for small effects. MDE Define the smallest useful lift: p1 = 11%, so delta = 1…
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in