Three comments: 1. If there is no right censoring (and it appears not), I would use lmer on the awakening times, glmer on the FullyOriented variable. That is, I agree with Burt. Another option is GEE models
2. If you want to use a Cox model, then you can a. Add "+ cluster(id)" to the model statement. This adds a robust variance, and is closely related to GEE. b. Use coxme to fit a mixed effects model. Terry Therneau ______________________________________________ R-help@r-project.org 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.
