[R-sig-ME] Overdispersion and model selection: glmmadmb vs. glmer

[David Duffy]

On Mon, 26 Aug 2013, Luca Corlatti wrote:

> My data are counts showing overdispersion. I therefore fitted my models 
> using the function glmmadmb with family=nbinom
> [AND] using the function 
> glmer, with family=poisson, adding the observation-level as a random 
> factor (1|obs) to account for overdispersion, as recently suggested. In 
> this case, however, visual inspection of residuals for the global model 
> were not very satisfactory. After running the model selection, the 
> results were quite different from those obtained with glmmadmb (not 
> dramatically different, but still...).

One is assuming chi-square and gaussian distribution of the REs 
respectively.  One can also fit "nonparametric" mixed models with 
mixtures (eg of gaussians) for the RE distribution.  Often there is not 
a lot of power to test different distributions of the latent variables.

Cheers, Davidl Duffy.

| David Duffy (MBBS PhD)                                         ,-_|\
| email: davidD at qimr.edu.au  ph: INT+61+7+3362-0217 fax: -0101  /     *
| Epidemiology Unit, Queensland Institute of Medical Research   \_,-._/
| 300 Herston Rd, Brisbane, Queensland 4029, Australia  GPG 4D0B994A v