Cookie preferences
We use cookies for analytics. Privacy Policy You can accept or decline non-essential tracking.
Practical guide to mde ab test: formulas, workflow, implementation pitfalls, and a direct execution playbook with Sample Size Calculator.
Go to tool
A/B test sample size calculator (Evan Miller formula).
Minimum Detectable Effect (MDE) is the smallest improvement your A/B test is designed to reliably detect. If your MDE is 5%, the test will catch a real 5% lift most of the time — but it will miss a 2% lift.
MDE is not about what you *hope* to see. It is about what your traffic can *afford* to measure.
For a two-sample proportion test at 80% power and alpha = 0.05, the required sample size per variant is approximately:
n = 16 * p * (1 - p) / delta^2
Where p is the baseline conversion rate and delta is the absolute MDE. The constant 16 comes from (Z_alpha/2 + Z_beta)^2 with standard values (1.96 + 0.84)^2 = 7.84, doubled for two variants and rounded.
Sample size grows with the *square* of MDE reduction. Halving MDE from 5% to 2.5% quadruples the required traffic. Here is a concrete table for a 10% baseline conversion rate:
| MDE (absolute) | Sample per variant | Total traffic (2 variants) |
|---|---|---|
| 5 pp | ~1,150 | ~2,300 |
| 3 pp | ~3,200 | ~6,400 |
| 2 pp | ~7,200 | ~14,400 |
| 1 pp | ~28,800 | ~57,600 |
| 0.5 pp | ~115,200 | ~230,400 |
Translate the lift into money. If your site converts at 3% and gets 100K visitors/month:
Ask: is $50K/month worth 5 weeks of testing? Usually yes. But if 0.5 pp lift = $25K and requires 20 weeks, probably not.
Open Sample Size Calculator, plug in your baseline rate and target MDE, and see whether your traffic can support the test duration.
This article is reviewed by the Tools Hub editorial team for factual accuracy, practical relevance, and consistency with current product workflows.
Last reviewed:
Practical guide to sample size signup test: formulas, workflow, implementation pitfalls, and a direct execution playbook with Sample Size Calculator.
Practical guide to stop rules ab test: formulas, workflow, implementation pitfalls, and a direct execution playbook with A/B Test Calculator.
Practical guide to multivariate vs ab test: formulas, workflow, implementation pitfalls, and a direct execution playbook with A/B Test Calculator.
Practical guide to false positive ab test: formulas, workflow, implementation pitfalls, and a direct execution playbook with A/B Test Calculator.