I am working on building a generalized linear mixed-effects model with Poisson distributed errors. I worked through it using glmer() in the lme4 package, but realized that my model is very over-dispersed, and I will need to go the negative binomial regression route. According to this tutorial (which has been very helpful):
According to this tutorial, there are 2 packages that I could use to do negative binomial GLMMs: gamlss.mx, and glmmADMB Problem is, I can't even load the packages. For gamlss.mx, I seem to be able to install it, but then it won't load. R says that the package does not exist (or isn't where I'm saying it is?). Could there be some problem with the naming of it (it's called gamlss.mx but R seems to be trying to load gamlss and not finding it?).
> utils:::menuInstallPkgs()
--- Please select a CRAN mirror for use in this session ---
Warning: dependency ‘gamlss’ is not available
trying URL 'http://probability.ca/cran/bin/windows/contrib/2.12/gamlss.mx_4.0-4.zip'
Content type 'application/zip' length 53000 bytes (51 Kb)
opened URL
downloaded 51 Kb
package 'gamlss.mx' successfully unpacked and MD5 sums checked
The downloaded packages are in
C:\Users\Mata\AppData\Local\Temp\Rtmp6SfELM\downloaded_packages
> local({pkg <- select.list(sort(.packages(all.available = TRUE)),graphics=TRUE)
+ if(nchar(pkg)) library(pkg, character.only=TRUE)})
Loading required package: gamlss
Error: package 'gamlss' could not be loaded
In addition: Warning messages:
1: package 'gamlss.mx' was built under R version 2.12.2
2: In library(pkg, character.only = TRUE, logical.return = TRUE, lib.loc = lib.loc) :
there is no package called 'gamlss'
