Definition: BIC

Category: Memobust Glossary

Criterion for model selection among a finite set of models. It is based, in part, on the likelihood function (Method: EBLUP Unit level for Small Area Estimation).

Measure of the relative goodness of fit of a statistical model BIC=k log(n)-2log(lik) where k is the number of parameters in the model, n is the number of observation and lik is the maximum value of the likelihood function (Method: EBLUP Area Level for Small Area Estimation (Fay-Herriot)). https://ec.europa.eu/eurostat/cros/content/memobust-glossary-pdf-file_en