Displaying 1 result from an estimated 1 matches for "mat2_1".
Did you mean:
mat2,1
2008 Dec 28
1
Random coefficients model with a covariate: coxme function
...or covar. Should I
introduce a third variance matrix per center and
redefine the groups as follows?
ugroup<-paste(rep(1:32, each=3), rep(c(0:1,"z"), 32), sep='/') #unique groups
mat1_1<-bdsmatrix(rep(c(1,1,1,1,1,1), 32),
blocksize=rep(3,32), dimnames=list(ugroup, ugroup))
mat2_1<-bdsmatrix(rep(c(0,0,0,1,0,0), 32),
blocksize=rep(3,32), dimnames=list(ugroup, ugroup))
mat3_1<-bdsmatrix(rep(c(0,0,0,0,0,1), 32),
blocksize=rep(3,32), dimnames=list(ugroup, ugroup))
group<-paste(data1$centers, data1$treat, data1$covar, sep="/")
fit3<- coxme(Surv(y, uncens)~...