Hello!
I am using glmmML for a logitic regression with random effect.
I use the posterior.mode as an estimate for the random effects.
These can be very different from the estimates obtained using SAS , NLMIXED
in the random with out= option. (all the fixed and standard error of random
effect estimators are almost identical)
Can someone explain to me why is that.
The codes I use:
R:
glmm1<-glmmML(mort30 ~ x , data=dat2,cluster=hospital,family=binomial)
print(sort(glmm1$posterior.mode))
SAS:
*
proc* *nlmixed* data*=*dat*;*
eta = b0 + b1*x+ u;
expeta = exp(eta);
p = expeta/(*1*+expeta);
model mort30 ~ binomial(*1*,p);
random u ~ normal(*0*,s2) subject=hospital out=blue;
*run*;
*
proc* *sort* data=blue;by estimate;
*
proc* *print* data=blue;*run*;
**
*THANKS FOR THE HELP*
*RON*
[[alternative HTML version deleted]]
______________________________________________
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.
