Franco, What about calling the BUGS model below from R using BRUGS?
Regards, -Cody francogrex <[EMAIL PROTECTED] com> To Sent by: r-help@stat.math.ethz.ch [EMAIL PROTECTED] cc at.math.ethz.ch Subject [R] Hierarchical models in R 05/14/2007 11:40 AM Is there a way to do hierarchical (bayesian) logistic regression in R, the way we do it in BUGS? For example in BUGS we can have this model: model {for(i in 1:N) { y[i] ~ dbin(p[i],n[i]) logit(p[i]) <- beta0+beta1*x1[i]+beta2*x2[i]+beta3*x3[i] } sd ~ dunif(0,10) tau <- pow(sd, -2) beta0 ~ dnorm(0,0.1) beta1 ~ dnorm(0,tau) beta2 ~ dnorm(0,tau) beta3 ~ dnorm(0,tau) } where we put a prior on the parameters betas, but the sd of the priors is determined along with the parameters in a full bayesian model. I know that there are MCMC packages in R but I didn't see one that can do the hierarchical stuff. Thanks -- View this message in context: http://www.nabble.com/Hierarchical-models-in-R-tf3754157.html#a10609656 Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@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. ______________________________________________ R-help@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.