It Is Common When Fitting Multilevel Models to Start with a Simple

Multiple Choice

It is common when fitting multilevel models to start with a simple model, and build it up by adding new terms and re-estimating the model. If you want to compare the fit of a multilevel model with a simpler variant of the same model, what estimation method must you use?

A) Ordinary least squares
B) Maximum likelihood
C) Restricted maximum likelihood
D) Generalized least squares