Definition: AIC

Category: Memobust Glossary

Measure of the relative goodness of fit of a statistical model AIC = 2k - 2log(lik), where k is the number of parameters in the model and lik is maximum value assumed by the likelihood function. https://ec.europa.eu/eurostat/cros/content/memobust-glossary-pdf-file_en
Source:
Eurostat, ESSnet "Memobust", "Memobust Glossary" (part of the Memobust Handbook on Methodology of Modern Business Statistics), March 2014
Created:
Updated: