Mixed conditional logit model
The 'lmer' function in library(lme4) and the 'glmmPQL' function in
library(MASS) both will estimate mixed-effects logit / logistic
regression models. (If anyone thinks there is a difference between
'logit' and 'logistic regression' models, I hope they will disabuse me
of my ignorance.)
Hope this help.
Spencer Graves
Ryuichi Tamura wrote:
Hi, Sven M?ller <sven.mueller <at> tu-dresden.de> writes:
i wonder whether it is possible to estimate a mixed (random parameters)
logit model in R.
I wrote a collection of R functions for estimating discrete choice models by simulated maximum likelihood. It includes: - likelihood and gradient functions for estimating mixed mnl, mixed panel mnl with some specific random structures for coefs (normal, lognormal, triangular, uniform) - some IIA testing functions includes 'artificial variable test' in Mcfadden and Train(2001) - functions for generating halton sequences for 'efficient' simulation. Please email me if you interested in. However, it is not so difficult to write programs for your own needs. URL for main reference is Kenneth Train's Home Page: http://elsa.berkeley.edu/~train/ My R functions is based on GAUSS program listed in this site. Regards, Ryuichi Tamura
______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.