In the context of power analysis in experimentation, "power" refers to the probability that the experiment will detect an effect if there is one. In other words, it's the likelihood that if a change or difference truly exists, the experiment will correctly identify it.

Power is directly related to the Minimum Detectable Effect (MDE), the number of days or exposures, and the allocation. The MDE is the smallest change in the metric that the experiment can detect. The number of days or exposures refers to how long the experiment is active and the number of users enrolled in it. The allocation is the percentage of traffic that participates in the experiment.

By adjusting these three variables, we can increase or decrease the power of an experiment. For instance, a larger allocation or a longer-running experiment can increase the power, making it more likely to detect a true effect. Conversely, a smaller MDE or a shorter experiment can decrease the power, making it less likely to detect a true effect.

Join the #1 Community for Product Experimentation

Connect with like-minded product leaders, data scientists, and engineers to share the latest in product experimentation.

Try Statsig Today

Get started for free. Add your whole team!

What our customers say about us

“Statsig takes away all the pre-work of doing experiments. It's really easy to setup, also it does all the analysis.”
Rei do pitaco
Elaine Tiburske
Data Scientist
“[Statsig] enables shipping software 10x faster, each feature can be in production from day 0 and no big bang releases are needed.”
Matteo Hertel
“Statsig gives Tavour best in class feature flag management combined with unparalleled A/B testing.”
Philip Vaughn
We use cookies to ensure you get the best experience on our website.
Privacy Policy