Platform
Developers
Resources
Pricing

Minimum Detectable Effect

The Minimum Detectable Effect (MDE) is the smallest change in a metric that an experiment can reliably detect. For instance, if the MDE is 1%, it means that if there's a true effect of 1% or larger on our metric, we expect the experiment will show a statistically significant result. If the effect is smaller than 1%, then it will likely fall inside the confidence intervals and not be statistically significant.

The MDE is influenced by several factors, including the number of days or exposures (how long the experiment is active and the number of users enrolled in it), and the allocation (the percentage of traffic that participates in the experiment).

In terms of using the power analysis tool, you can select the population used to determine the metric mean and variance and to estimate the number of exposures over time. The population types include everyone (analysis is based on the entire user base), targeting gate (analysis is scoped to the set of users that pass the selected feature gate), and past experiment (analysis is based on data collected from in a previous experiment).

The tool also allows for fixed allocation analysis (to understand how the length of the experiment impacts the MDE) and fixed MDE analysis (if the smallest effect size that the experiment should detect is known).

Remember, the population selected directly impacts the inputs of the analysis (mean, variance, number of users). To obtain reliable power analysis estimates, the metric values of the selected population should roughly match those of the users you'll be targeting in the experiment.

Try Statsig Today

Easy to start, simple to collaborate. It's for your whole team!

What our customers say about us

Testimonials
“We finally found a product that moves just as fast as we do and have been super impressed with how closely our teams collaborate.”
Whatnot
Rami Khalaf
Product Engineering Manager
quote
“Statsig has been a game changer for how we combine product development and A/B testing.”
Recroom
Joel Witten
Head of Data
quote
“Statsig has enabled us to quickly understand the impact of the features we ship.”
Headspace
Shannon Priem
Lead PM
quote
We use cookies to ensure you get the best experience on our website.
Privacy Policy