[R] coxme - fitting random treatment effect nested within centre

Rasanga Ruwanthi ruwanthi_kdr at yahoo.com
Wed Mar 5 10:12:08 CET 2008


Dear all,

I am using "coxme" function in Kinship library to fit random treatment effect nested within centre. I got 3 treatments (0,1,2) and 3 centres. I used following commands, but got an error. 

> ugroup=paste(rep(1:3,each=3),rep(0:2,3),sep='/')
> mat1=bdsmatrix(rep(c(1,1,1,1,1,1,1,1,1),3),blocksize=rep(3,3),dimnames=list(ugroup,ugroup))
> mat2=bdsmatrix(rep(c(0,0,0,0,0,0,0,0,1),3),blocksize=rep(3,3),dimnames=list(ugroup,ugroup))
> group=paste(dat1$centre,dat1$treat,sep='/')
> coxme(Surv(time,status) ~ as.factor(treat), data=dat1,random= ~1|group,varlist=list(mat1,mat2),rescale=F,pdcheck=FALSE)

Error in coxme.fit(X, Y, strats, offset, init, control, weights = weights, : 
Random effects variance is not spd
 
Could anyone help me correcting this error? 
Many thanks in advance.
Ruwanthi


      ____________________________________________________________________________________
Looking for last minute shopping deals?



More information about the R-help mailing list