Hi All
I was wondering is their a problem in using ANCOVA when the covariate is
strongly associated with one of the dependant variables (along the lines
of the problem of collinearity in multiple regression)?
Regards
Graham
--
Dr G.S.Clarke
Lecturer in Physiology & Biometry
Faculty of Health Studies
University of Wales, Bangor
Fron Heulog
Ffriddoedd Road
Bangor
Gwynedd LL57 2EF
Tel: 01248 383157
e-mail: [log in to unmask]
|