Skip to content
Free tool

Minimum detectable effect (MDE) calculator

If your traffic is fixed, work backwards: see the smallest lift a test of a given length can reliably detect.

What you can run

%
days

How long you're willing to run the test.

Minimum detectable effect

19%

In this window you can reliably detect a lift from 3% to 3.57% or larger.

Visitors per variant

14,000

Detectable target rate

3.57%

What minimum detectable effect means

Minimum detectable effect (MDE) is the smallest lift your test can reliably catch. The sample size calculator starts from the lift you want and tells you the traffic you need. This one flips that around: it takes the traffic you actually have over a fixed window and tells you the smallest lift that traffic can detect.

MDE = (zα + zβ) × √(2 × p(1 − p) / n) / p

Here n is the visitors per variant your window provides, p is the baseline conversion rate, and zα and zβ come from your confidence and power. The result is a relative lift: a 12% MDE on a 3% baseline means you can detect a move to roughly 3.36% or more.

When to reach for this calculator

Use it when traffic is the thing you cannot change. If your store gets 60,000 visitors a month and you can run a test for two weeks, this tells you whether a realistic lift is even detectable in that time. If the answer is a 20% MDE, small tweaks are off the table and you should test changes bold enough to clear that bar.

FAQ

Frequently asked questions

Stop guessing what to test

A calculator tells you whether a test is worth running. Spar finds the tests worth running: it audits your storefront, ranks the gaps by revenue impact, and drafts the variations. Start a 14-day free trial.