[R] A warning message when using mix package.

From: Li, Jia <LI_at_nsabp.pitt.edu>
Date: Wed 20 Jul 2005 - 06:37:20 EST


Dear all,

I just start using package mix in R and am inexperienced with it. When I ran my program several times, I sometimes got the warning message, and sometimes not :

Warning message:

Loglik converged before variable 2 ; beta may be infinite. in: fitter(X, Y, strats, offset, init, control, weights = weights,

I cannot find what is wrong with my program. Does anyone have an idea with it and whether this would affect my results? Any help would be appreciated.

Thanks!

By the way, I copy a part of my program and hope it would help,

beta <- c(0, 0,0,0,0) # 'True' coefficients

#------------make a matrix of covariates-----------------------#

Y=cbind(z4,z5,z1,z2,z3)

s<-prelim.mix(Y,2)

#----------------------------run MI------------------------------#

MI<-vector("list",10)

fit.model.mi<-vector("list",10)

rngseed(1234567) # set random number generator seed

for (i in 1:10){

thetahat <- em.mix(s)

newtheta <- da.mix(s, thetahat, steps=2000, showits=TRUE)

MI[[i]] <- imp.mix(s, newtheta)

}

        [[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 Received on Wed Jul 20 06:41:22 2005

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:33:50 EST