[R-sig-ME] glmmadmb Negative binomial dispersion parameter

[Mollie Brooks]

Hi Marte,

Overdispersion isn’t usually a concern with the negative binomial distribution. It’s a problem with distributions where the variance is strictly tied to the mean, like the Poisson. 

There are two different ways that glmmadmb lets the variance relate to the mean. See the details of the help file for descriptions of "nbinom" and "nbinom1". You could compare the AIC of models fit with each of these if you want to see which one is best. I don’t know of other diagnostics, but maybe someone else will chime in.

cheers,
Mollie

------------------------
Mollie Brooks, PhD
Postdoctoral Researcher, Population Ecology Research Group
Department of Evolutionary Biology & Environmental Studies, University of Zürich
http://www.popecol.org/team/mollie-brooks/


> On 23Feb 2016, at 15:02, Marte Lilleeng <mlilleeng at gmail.com> wrote:
> 
> Hello everyone.
> I wonder if you can help me with the following questions?
> 
> 1) How is the Negative binomial dispersion parameter calculated in glmmadmb?
> 
> 2) Is there,as for mixed effects poisson models (glmer), a *rule of thumb*
> for when the dispersion parameter is representing trouble (overdispersion)?
> I learned from Zuur and Ileno that for a mixed effects poisson mod the
> dispersion is ok as long as it is not above 1.3-1.4(calculated this way;
> 
> E <- residuals (modelname)
> 
> pb <- length(fixef(modelname)+1) # +1 due to random intercept variance
> 
> overdisp <- sum(E^2)/(nrow(dataset)-pb)
> 
> 3) How do you recommend to do the model validation for glmmadmb with
> negative binomial error structure?
> 
> Best regards from
> "New to mixed models with NB", Marte Lilleeng
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
> 


	[[alternative HTML version deleted]]