Hi Everyone,
my outcome is a number between 0 and 1. I have a fair number of 0s and 1s.
I would like to fit a model using 5 binary predictors. I have 6 repeated
measurements from each respondent, each with a different set of covariates.
I've done a logit transform on my outcome. I've subtracted and added 1E-16
to the 1's and 0's, respectively, to make this work.
I want to implement this in MCMCglmm. I just wanted to check:
a) I can use a gaussian family because I have already done the transform
b) Is R=list(V=1,fix=1) appropriate in this case
c) when I make predictions, I have to add 1 to linear predictor?
Thanks
Mark
[[alternative HTML version deleted]]
______________________________________________
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.
