Hi Arthur (and all),
could you indicate how ASREML deals with uninformative groups for 0/1
traits? Can uninformative groups accidentally "become informative"
numerically through the fitting of covariates (for example), or are these
groups removed before any other effects in the model are considered?
Also, are there any tricks to running bivariate analyses with one binary
and one continuous trait? It seems trait order is important (ie 0/1 trait
must be specified first). Can either !log or !prob be used, and does
convergence usually need to be helped along with fixing some parameters
(for example)?
Any comments much appreciated.
Cheers
Kim
Kim Bunter
Research Scientist
Animal Genetics and Breeding Unit
University of New England
Armidale, NSW, 2351
AUSTRALIA
Ph (ISD): -61-2-67733788
Fax (ISD): -61-2-67733266
email: kbunter@metz.une.edu.au
--
Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml