AI engineering glossary · Statistics inference
What is FDR (false discovery rate)?
False discovery rate (also called FDR): The expected fraction of rejected null hypotheses that are actually false alarms. Controlling it is less strict than controlling the family-wise error rate and suits screening many candidates, such as genes or features.
False discovery rate: an example
If 50 features are flagged as significant and the rate is controlled at 10 percent, about 5 of them are expected to be false leads.
Related terms
More Statistics inference terms
- Family-wise error rate
- Fisher information
- Fisher's exact test
- Frequentist inference
- Generalised linear model
- Guardrail metric
- Heteroscedasticity
- Homoscedasticity
Where you learn it
False discovery rate is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.