What does "Overpowered Test" mean?
Definition of Overpowered Test in the context of A/B testing (online controlled experiments).
What is an Overpowered Test?
An overpowered A/B or MVT test is one which has relatively poor probability for detecting a specified minimum effect of interest (MEI). Getting a statistically significant result from such a test is a poor evidence for large discrepancies from the null hypothesis versus observing the same p-value from a less powerful test. This becomes very obvious when examining the upper confidence limit of a one-sided or two-sided confidence interval.
A test can be overpowered with respect to larger alternatives while being properly powered or even underpowered versus alternatives closer to the null hypothesis since power is calculated at a point. By definition in frequentist statistics the smaller the magnitude of the effect of interest, the less powerful the test, all else being fixed.
Like this glossary entry? For an in-depth and comprehensive reading on A/B testing stats, check out the book "Statistical Methods in Online A/B Testing" by the author of this glossary, Georgi Georgiev.
Articles on Overpowered Test
The Importance of Statistical Power in Online A/B Testing
blog.analytics-toolkit.com
Statistical Power, MDE, and Designing Statistical Tests
blog.analytics-toolkit.com
Related A/B Testing terms
Statistical PowerType II ErrorbetaSee this in action
About the author
Statistical Methods in Online A/B Testing
Take your A/B testing program to the next level with the most comprehensive book on user testing statistics in e-commerce.
Learn moreGlossary index by letter
Select a letter to see all A/B testing terms starting with that letter or visit the Glossary homepage to see all.
