[R-sig-ME] Question about truncated poisson vs. normal poisson, "minus one" & Co. in winbugs or glmer

[David Atkins]

Ulf--

In addition to Alain's comments, you might consider MCMCglmm -- it can 
fit a Bayesian hurdle mixed model, but uses syntax much closer to 
glmer() and other "standard" R formula-based regression models.

BUGS and cousins will be far more flexible if you need to add something 
"special" to your model (e.g., longitudinal or geographical 
correlation), but from your description, I think you could fit your 
model with MCMCglmm (which should also be much faster than BUGS, I believe).

Jarrod Hadfield (developer of MCMCglmm) has a JSS paper and course notes 
describing functions:

http://cran.r-project.org/web/packages/MCMCglmm/index.html

And, we included R code demonstrating how to fit hurdle mixed models to 
accompany the following paper:

Atkins, D. C., Baldwin, S., Zheng, C., Gallop, R. J., & Neighbors, C. 
(in press). A tutorial on count regression and zero-altered count models 
for longitudinal addictions data.

which can be found:

http://depts.washington.edu/cshrb/newweb/statstutorials.html

Finally, another option could be glmmADMB, which can fit hurdle models 
via its two sub-components: 1) logit mixed model, and 2) truncated count 
mixed model.

Hope that helps.

cheers, Dave

-- 
Dave Atkins, PhD
University of Washington
datkins at u.washington.edu
http://depts.washington.edu/cshrb/

August 1 - October 30:

Universitat Zurich
Psychologisches Institut
Klinische Psychologie
Binzmuhlestrasse 14/23
CH-8050 Zurich

+41 44 635 71 75