MathLiveAkaike information criterion
Scores a statistical model by its maximised likelihood penalised for the number of parameters, so that lower values indicate a better trade-off between fit and complexity. It is used to compare candidate models fitted to the same data.
\mathrm{AIC} = 2k - 2\ln\left(\max_{\theta_1,\dotsc,\theta_k}\Pr(x_1,\dotsc,x_n \mid \theta_1,\dotsc,\theta_k)\right)What the symbols mean
| Akaike information criterion value (lower is better) | |
| number of estimated parameters in the model | |
| number of observations | |
| observed data realisations | |
| model parameters | |
| likelihood function of the parameters given the data |
About this formula
- FieldStatistics
- TopicModel selection
- LevelUniversity
- Also calledAIC, model selection criterion, AIC formula, maximum likelihood model selection, information criterion for model comparison, Akaike criterion
- SourceWikidata Q1662573
Write it in Obsidian
MathLive is a free visual math editor for Obsidian. Run Find a formula, type “akaike information criterion”, and it goes into your note as editable LaTeX. You can also scan formulas from screenshots, PDFs and handwriting.