Akaike information criterion
Definition taught in Model selection for stochastic models, part of Statistical learning
Akaike information criterion
| Type | Definition |
| Taught in | Model selection for stochastic models |
| Part | Statistical learning |
| Questions using it | 4 |
The penalty is 2d_k:
k^*\approx\arg\min_k\mathrm{AIC}_k, \qquad \mathrm{AIC}_k=-2\ell(\widehat\Psi_k;X_{\mathrm{all}},M_k)+2d_k.
Used in
- Taught in Model selection for stochastic models, where the derivation and examples are.
- Also used in Introduction to generalised linear models · Standard errors, and models for counts · Underdispersion, positive responses, and quasi-likelihood · Categorical responses · Paired comparisons, and how far a fit is from the data · Statistical classifiers and discriminant analysis · Logistic regression · Forecasting
- Questions that use it (4) — BIC and AIC by hand · A tempting wrong turn (answer) · Question 21 (answer) · Question 22 (answer)
- All 7 questions on Model selection for stochastic models
See also
Bayesian information criterion · Extended information criterion · Deviance · Analysis of deviance · Laplace approximation · Dropping terms that do not scale with n · Reading the BIC · Cross-validation of the likelihood