AI engineering glossary · Statistics inference
What is likelihood ratio test?
Likelihood ratio test: A test that compares two nested models by looking at twice the difference in their log-likelihoods, which follows a chi-square distribution under the simpler model. It asks whether extra parameters improve the fit significantly.
Likelihood ratio test: an example
Comparing a logistic model with and without a city predictor: a large statistic favours keeping city.
Related terms
More Statistics inference terms
- Log-likelihood
- Mann-Whitney U test
- Margin of error
- Maximum a posteriori estimation
- Minimum detectable effect
- Multiple comparisons problem
- Non-parametric test
- Novelty effect
Where you learn it
Likelihood ratio test is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.