The Bayesian Information Criterion (BIC) is widely used for variable selection in mixed effects models. However, its expression is unclear in typical situations of mixed effects models, where simple definition of the sample size is not meaningful. We derive an appropriate BIC expression that is consistent with the random effect structure of the mixed effects model. We illustrate the behavior of the proposed criterion through a simulation experiment and a case study and we recommend its use as an alternative to various existing BIC versions that are implemented in available software.
"A note on BIC in mixed-effects models." Electron. J. Statist. 8 (1) 456 - 475, 2014. https://doi.org/10.1214/14-EJS890