Conditional Model Selection in Mixed-Effects Models with <b>cAIC4</b>

Model selection in mixed models based on the conditional distribution is appropriate for many practical applications and has been a focus of recent statistical research. In this paper we introduce R package cAIC4 that allows computation Akaike information criterion (cAIC). Computation AIC needs to take into account uncertainty random effects variance therefore not straightforward. We fast stable implementation calculation cAIC (generalized) linear estimated with lme4 additive gamm4. Furthermore, offers stepwise function an automated scheme cAIC. Examples possible are presented illustrate impact easy handling package.