[R] Estimate zero inflated mixed model parameter

[Ben Bolker]

 <xqzhang85 <at> yahoo.com> writes:

> 
> Hi, I can not estimate the zero inflated mixed model parameters successfully.
If it is possible, would you
> please help me write the code? In my case, I consider the location as a random
effect. My data are:
> 
> location y x1 x2 x3
> 1    
> 1
> 1
> 2
> 2
> 2
> 3
> 3
> 3    

  We need more detail about your question, and preferably about your
attempts to solve the question for yourself (to "do your homework").
To my knowledge, the glmmADMB and MCMCglmm packages are your only
options for fitting zero-inflated mixed models in R -- glmmADMB is
less flexible but possibly easier to get started with.  Something like

library(glmmADMB)
glmm.admb(y~x1+x2+x3,random=~1,group="location",family="poisson",
  zeroInflation=TRUE, data=dat)

  but see the help page for details -- this is all from memory.

Follow-ups should probably go to the r-sig-mixed-models list.

  Ben Bolker