Re: bivariate animal model

From: <brian.cullis_at_DPI.NSW.GOV.AU>
Date: Wed, 3 Jun 2009 14:40:05 +1000

Dear arthur

I enclosed a revised job that runs.
[Renamed as bvanimal.txt because was not allowed]

Since the responses are on different animals, I have fixed the residual
correlation to ZERO

2) Since you are using only 2 traits, you cannot use FA models.
The FA model has 4 parameters but there are only three degreesof freedom
for parameters in a 2x2 symmetric matrix.
****yes this is true for this example, but it is possible though perverse
perhaps to use FA models for a 2x2 structure, should you want to be able
to cope with reduced rank models
by suitably fixing parameters to zero.

3) The job is set up to define PATHs 2 and 3 therefore you need to specify
2 or 3 as the argum,ent.

4. 0.1 0.1 0.1
is invalid as starting values for an unstructured matrix as this is a
singular matrix. If you supply
0 0 0
ASReml will supply starting values.

warm regards

Brian Cullis
Research Leader, Biometrics &
Senior Principal Research Scientist
NSW Department of Primary Industries
Wagga Wagga Agricultural Institute

Visiting Professorial Fellow
School of Mathematics and Applied Statistics
Faculty of Informatics
University of Wollongong

Faculty of Agriculture, Food & Natural Resources
The University of Sydney

Adjunct Professor
School of Computing and Mathematics
Charles Sturt University

Phone: 61 2 6938 1855
Fax: 61 2 6938 1809
Mobile: 0439 448 591
Received on Thu Jun 03 2009 - 14:40:05 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)