glmm for binomial data? (OT) - R-help

Mon, Oct 28, 2002 1:59 PM #

A while ago (April 2002) there was a short thread on software for generalized 
linear mixed models. 

Since that time, has anyone written or found R code to use a glmm to analyze 
binomial data?  I study CWD in white-tailed deer, and I'd like to do a 
similar analysis as Kleinschmidt et al. (2001, Am. J. Epidemiology 153: 
1213-1221) used to assess control for spatial structure in malaria incidence 
in South Africa.  They used SAS PROC MIXED in an iterative procedure with a 
poisson model, although due to widely varying sample sizes I'd prefer to 
treat my data as binomial (e.g., CWD pos or neg rather than number of CWD pos 
deer).

Thanks,

Damien

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

Brian Ripley

Mon, Oct 28, 2002 8:30 PM #

Same as then.

glmmPQL in MASS (approximate, but not a bad approximation)
glmm in GLMMGibbs (needs careful tuning in the binomial case, but
has worked for me).

New info:

There is a section and a couple of worked examples in MASS4.  The
best method there uses R/S+C code which is not yet available to public
release, but we expect it to be within 6 months.

On Mon, 28 Oct 2002, Damien O. Joly wrote:

Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

Andrew Perrin

Tue, Oct 29, 2002 6:08 AM #

I used glmmPQL to estimate multilevel (3-level) probit models.  I can try
to dig up the code if you're interested.

Andy Perrin

----------------------------------------------------------------------
Andrew J Perrin - http://www.unc.edu/~aperrin
Assistant Professor of Sociology, U of North Carolina, Chapel Hill
clists at perrin.socsci.unc.edu * andrew_perrin (at) unc.edu

On Mon, 28 Oct 2002, Damien O. Joly wrote:

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._