Minimum detectable effect (MDE) calculator
Find the smallest lift your traffic can reliably detect in a set number of weeks. Tells you whether a test is worth running before you start.
Medium changes are measurable. Test clear differences in copy, pricing presentation or layout.
How it works
The minimum detectable effect is the smallest true lift your test has a good chance (your chosen power) of spotting. It's the sample size question turned around: instead of "how many visitors do I need for a 10% lift?", it asks "with the visitors I have, what's the smallest lift I can see?"
If the answer is 40%, a test of a small tweak is a waste of your traffic: even if it works, you won't be able to tell. Test bigger changes, or run longer.
Example: 2,000 visitors a week, a 5% conversion rate, 4 weeks, 95% confidence and 80% power can detect a lift of about 29%.
Questions people ask
What is a good minimum detectable effect?+
Whatever your traffic allows and your business cares about. Big sites can detect 2 to 5% lifts; most startups can only detect 20% or more in a month, so they should test bold changes.
How do I lower my MDE?+
Run the test longer, send more traffic to the tested page, test a step with a higher conversion rate, or accept slightly lower confidence.
Is MDE relative or absolute?+
This calculator reports a relative lift: a 20% MDE on a 5% conversion rate means detecting a change to 6%.
Learn more
More free tools
Want the tests run for you?
AI agents read your analytics and payments, find where you lose the most money, build the fix and test it. Every test is judged on revenue, not clicks. Plans from $29 a month.