Hi everybody,
I have built a model that includes subject ID as a random effect, and has a
continous variable (time) and I want to test whether the slope of this line
differs between treatments (this is tested with the interaction between
treatment and "time").
My question now is that I also want to include regressors that might explain
variation in this slope between subjects (and of which I have this one
estimate for the whole time period). How do I do this? If I just code it as
the same number for all the time points I have measured I am overestimating
my sample size don't I? (because I have not measured it for each time
point).
I am curious as to what you think about this
Thank you very much
Greetz
--
View this message in context:
http://www.nabble.com/random-effects-mixed-model%2C-different-regressors-tp18750857p18750857.html
Sent from the R help mailing list archive at Nabble.com.