[R-sig-ME] random effects specification

Sebastian P. Luque spluque at gmail.com
Mon Apr 7 15:49:10 CEST 2008


Fortunately, I have learnt to use unique factor levels for subjects,
only as a lucky accident though, but am glad it's a good convention to
use in mixed models.

Thanks everyone for your useful feedback, this has been very instructive!



More information about the R-sig-mixed-models mailing list