New tool in R simplifies testing for effects in mixed models.
The varTestnlme package for R helps test which effects should be fixed or random in mixed-effects models. It uses likelihood ratio tests to check if certain variances and covariances can be set to zero. This tool can test for fixed effects and variance components at the same time in linear, generalized linear, or nonlinear mixed-effects models. The package works with models fitted via lme4, nlme, or saemix. The researchers provide examples using real datasets to demonstrate the tool's effectiveness.