[ADMB Users] Running glmm.admb

[H. Skaug]

Hi Nicole,

A random intercept model should be:

Model1<-glmm.admb(CDP~Slp+Evn+LP+VegCom,random=~1,group="Is",family="nbinom",data=

If you would like a random effects for some of the explanatory
variables (for instance Evn+LP) as well you can use

Model2<-glmm.admb(CDP~Slp+Evn+LP+VegCom,random=~Evn+LP,group="Is",family="nbinom",data=

Please feel free to contact me directly if you have further questions.

Hans


On Mon, Mar 30, 2009 at 3:05 AM, Nicole Schumann <nsc at deakin.edu.au> wrote:
> Hi,
>
> I'm very new to R and gmml.admb so my apologies if my question is very
> basic.  I'm looking at habitat preferences of seabirds on several
> islands.  I have a number of fixed predictor variables as well as
> island which, in my understanding, I need to include as a random
> variable to account for pseudoreplication.  My response variable (CDP
> - ie. the number of burrows of a petrel species per quadrat) is
> zero-inflated and overdispersed so I'm trying to use glmm.admb for count
> data with a negative binomial distribution. However, it requires a grouping
> variable which confuses me because surely that's also my random variable
> (ie. island)?
>
> Also, when I write my command, I get the following error message:
>
> Error: unexpected input in
> "Model1<-glmm.admb(CDP~Slp+Evn+LP+VegCom,random=~Is,family=?"
>
> Can anyone suggest what I need to do?
>
> Thanks
>
> Nicole Schumann BEnvSc(Hons)
> PhD Candidate
> School of Life and Environmental Sciences
> Deakin University, Australia
>
>
>
>
>
>
>
>
> _______________________________________________
> Users mailing list
> Users at admb-project.org
> http://lists.admb-project.org/mailman/listinfo/users
>