MDE (Minimum Detectable Effect)
The smallest difference that, if it exists, can be reliably detected in a statistical test.
The smallest performance difference between two variants (e.g., conversion rate, revenue per visitor) that a statistical test is able to reliably detect, given the sample size, confidence level, and statistical power. In a CRO and A/B testing approach, the MDE helps define the minimum magnitude of change that the test can identify as statistically significant.
An MDE that is too high risks masking real but small gains, while an MDE that is too low requires large volumes of traffic to be detected with certainty. It is therefore an essential parameter to adjust based on business stakes, available traffic volume, and test objectives. When properly calibrated, it helps prioritize tests based on their potential impact and avoid decisions based on random fluctuations.
Autres termes : Statistiques
View the full glossary- Frequentist Approach (A/B test)A statistical approach that estimates model parameters based solely on observed data, without using prior information.Statistiques
- Bayesian (A/B test)A statistical approach that uses probability to represent uncertainty about model parameters.Statistiques
- Statistical confidenceLevel of certainty one has in the results of a statistical test.Statistiques
- False NegativesResults that fail to detect an effect that is actually present.Statistiques
- False PositivesResults wrongly indicating that an effect is present when it is not.Statistiques
- Mann-Whitney U TestA non-parametric test used to compare two independent samples to determine whether they come from the same distribution.Statistiques