Re: testing contrasts in ASREML

Dear Ky,

re:
I have a question about the best way to fit contrasts and test for their
significance.

The data set contains varieties with contrasting effects, for example tall
vs
short.
I have fitted the following model where
tvs = dummy variable for contrasting tall versus short
gen = genotypes 1 to 96
and the usual design variables rep, column and row

yield ~ mu mv tvs !r gen rep column,
!f lin(row)
1 2 0
12 column AR 0.2
16 row AR 0.4
predict tvs

From the predict statement I can determine the effects of each level in
the
contrast and the SED. Is this what I should use to test the significance
of the
effects or can I use a Wald test?
I expected the fixed effects (with accompanying Wald statistics) to appear
under Analysis of Variance in the *.asr file but they don't. Is there are
reason for that?

1) tvs will appear in the ANOVA table if you list it before mv
i.e.
yield ~ mu lin(row) tvs mv !r gen rep column

The reason is that mv and anything listed after it is included in the
SPARSE stored equations
and therefore omitted from the ANOVA.

2) I gather tvs is actually a factor coding say 1=Tall 2=Short
so with the model as fitted, the SED is all that is available
Best wishes in the Name of Christ Jesus,
the Saviour of all who believe.

Arthur Gilmour PhD
Principal Research Scientist (Biometrics)
NSW Department of Primary Industries
Orange Agricultural Institute, Forest Rd, ORANGE, 2800, AUSTRALIA

mailto:Arthur.Gilmour_at_agric.nsw.gov.au
fax: 02 6391 3899; 02 6391 3922 Australia +61
telephone work: 02 6391 3815; home: 02 6364 3288;
mobile: 04 2764 3288 (no reception at home)
http://www.agric.nsw.gov.au/reader/17263

ASREML website: http://www.asreml.co.uk/
The ASReml discussion group ASREML-L_at_agric.nsw.gov.au
has reactivated. To join, mailto:arthur.gilmour_at_agric.nsw.gov.au

Cookbook: http://uncronopio.org/luis/asreml_cookbook.html
                        <> <> <> <> <> <> <>

<><><><><><><><><><><><><><><><><><><><><><><><><>

This message is intended for the addressee named and may contain
confidential information. If you are not the intended recipient or
received it in error, please delete the message and notify sender. Views
expressed are those of the individual sender and are not necessarily the
views of their organisation.
Received on Tue Nov 02 2004 - 14:10:26 EST