[R-sig-ME] GLMMs with unequal group sizes

[Grant T. Stokke]

Sorry, I should have been more clear.  The number of unused units is 
included.  The response variable is "Used", so that used units have Used=1 
and unused units have Used=0.

Thanks for the input.  I've been looking at the influence of the areas with 
many used units on parameter estimates (by removing areas 3 and 9), and they 
appear to be more influential than I would like.  Ideally, I'd like each 
study area to receive approximately equal weight in parameter estimation. 
Is that possible?  Would it be inappropriate to use the 'weight' option in 
glmer to give study areas more equal weight?  Any suggestions?

Thanks,

-Grant

----- Original Message ----- 
From: "Daniel Ezra Johnson" <danielezrajohnson at gmail.com>
To: "Grant T. Stokke" <gts127 at psu.edu>
Cc: <r-sig-mixed-models at r-project.org>
Sent: Thursday, June 11, 2009 8:56 AM
Subject: Re: [R-sig-ME] GLMMs with unequal group sizes


> On Wed, Jun 10, 2009 at 11:41 PM, Grant T. Stokke<gts127 at psu.edu> wrote:
>> Hello All,
>>
>> I would like to use GLMMs with a binary response variable (logit link) to
>> model the effects of three environmental covariates on whether resource
>> units were used or unused by a wildlife species.  I have 15 different 
>> study
>> areas, and very different numbers of used and unused units in each.  I'm
>> interested in using fixed effects parameters estimates to predict the
>> relative probabilities that resource units will be used across the entire
>> population of study areas.  Numbers of used and unused units in each area
>> look something like this:
>>
>> Area    Unused    Used
>> 01        281        2
>> 02        4415      1
>> 03        343        30
>> 04        256        1
>> 05        2052      4
>> 06        4050      1
>> 07        238        2
>> 08        743        3
>> 09        2476      18
>> 10        2524      1
>> 11        805        1
>> 12        754        4
>> 13        272        1
>> 14        52          1
>> 15        124        1
>>
>> I've been using study area as a grouping factor for a random intercept 
>> and
>> random slope effects:
>>
>> fullmodel<-glmer(Used~1+x1+x2+x3+(1+x1+x2+x3|Area), family=binomial,
>> data=mydata)
>
> Does this mean that the number of Unused units is not included
> anywhere in the model?
>