[R-sig-ME] [Fwd: Re: Wald F tests]

[Goedhart, Paul]

Hello,

Apparently Ben Bolker and Douglas Bates have different opinions on
testing fixed effects in GLMMs (see below). Does anyone know of any
(simulation) papers on this issue?

Ben Bolker wrote
> But ... LRTs are non-recommended (anticonservative) for comparing 
> fixed effects of LMMs hence (presumably) for GLMMs, unless sample 
> size (# blocks/"residual" total sample size) is large, no?

Douglas Bates wrote:
> If I were using glmer to fit a generalized linear mixed model I would 
> use likelihood ratio tests rather than Wald tests. That is, I would 
> fit a model including a particular term then fit it again without that

> term and calculate the difference in the deviance values, comparing 
> that to a chi-square.
>

Paul Goedhart, Biometris, Wageningen UR, The Netherlands