Re: soultions using xfa

craig
there are 5 sets of effects for SD because you are fitting XFA(SD,1).*
The MMEs are formed using the algorithm of Thompson et al 2003 in which we
include extra terms for the so-called common effect 'f'. the 5th level is
the blup of 'f'.
the blups for the other levels of SD are 1...4
WHen you use predict you have to use xfa(SD,1) variety to get the two way
table of predictions

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

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

Phone: 61 2 6938 1855
Fax: 61 2 6938 1809
Mobile: 0439 448 591
 






Craig Hardner <Craig.Hardner_at_CSIRO.AU>
Sent by: ASReml users discussion group <ASREML-L_at_AGRIC.NSW.GOV.AU>
16/12/2006 07:15 PM
Please respond to ASReml users discussion group

 
        To: ASREML-L_at_AGRIC.NSW.GOV.AU
        cc:
        Subject: soultions using xfa


Hi Folks
I am wanting to get solutions for a random factor at different levels of
the second factor where the Var/Cov matix has been estimated using xfa.
i.e In the model below I want to get solutions for TREE and FAM at the 4
different levels of SD. In the sln file there seems to be 5 solutions for
TREE, 4 for the levels of SD and another one. I am unsure how to use
PREDICT for this model?
Ta a lot for any help
TY8AS ~ SITE SITE.BLOCK SITE.ADENS,
         !r at(SITE,1).at(BLOCK,1).REP,
            at(SITE,1).at(BLOCK,3).ACOL,
            at(SITE,2).at(BLOCK,4).REP,
            at(SITE,2).at(BLOCK,5).REP,
            xfa(SD,1).TREE,
            xfa(SD,1).FAM,
           !f mv
5 2 2 !STEP 0.1
7 ACOL AR1 0.1
56 AROW AR1 0.1
7 ACOL IDEN
54 AROW AR1 -0.25
15 ACOL IDEN
57 AROW IDEN
21 ACOL IDEN
54 AROW IDEN
13 ACOL IDEN
29 AROW AR1 0.62
xfa(SD,1).TREE
xfa 0 xfa1 !ƶ !GP
4*0.022
0.0231 0.0985 0.0572 0.3518
TREE 0 AINV
xfa(SD,1).FAM
xfa 0 xfa1 !ƶ !GP
4*0.022
0.00369 0.0237 0.0230 0.0230
FAM 0 IDEN


Dr Craig Hardner
Project Leader Macadamia Improvement and Conservation
CSIRO Plant Industry
Queensland Bioscience Precinct
306 carmody Road
St lucia QLD 4067
ph: 07 3214 2659
fax: 07 3214 2920
email: craig.hardner_at_csiro.au



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 Fri Dec 17 2006 - 06:35:17 EST