Re: Predicting nesting values....

Dear Scott,

tch ~ mu Env mv !r Gen Gen.Cclass Gen.LocGroup Gen.LocGroup.Env
predict LocGroup

By default, ASReml ignores random terms in prediction unless they
are explicitly included, on the assumption that they are ERROR terms
(e.g. BLOCK effects).

So, terms including Gen and Class are ignored,
and the prediction just invloves mu and Env

83.03 + Ave of Env effects = 83.03 + 3.91 = 86.94

Furthermore, since LocGroup is a classification of Env,
Gen effects will sum to zero within levels of LocGroup
so adding !AVERAGE Gen

to make the prediction include terms Gen Gen.Cclass Gen.LocGroup
Gen.LocGroup.Env
does not change the predicted mean, it just changes (reduces) the SEs
because the accuracy
relates to the particula set of genotypes rather than the implicit
population of genotypes of which
the included genotypes are a random sample.

You can get different predictions for the levels of LocGroup by appending
  !PRESENT Env LocGroup

predict LocGroup !PRESENT Env LocGroup

Then the LocGroup 1 means will be of the Environments pertaining to
LocGroup 1
and the LocGroup 2 means will be of the Environments pertaining to
LocGroup 2

So, the following predictions are for

predict LocGroup !PRESENT Env LocGroup !AVERAGE Gen
predict LocGroup !PRESENT Env LocGroup

 Ecode is E for Estimable, * for Not Estimable

 Warning: mv_estimates is ignored for prediction

 ---- ---- ---- ---- ---- ---- ---- ---- 1 ---- ---- ---- ---- ---- ----
---- ----
 Env is averaged of combinations present in data
 Predicted values of tch
 Gen is averaged in fixed and random factors
 Cclass is ignored in the prediction (except
where specifically included

 LocGroup Predicted_Value Standard_Error Ecode
            2 87.8125 1.0115 E
            1 85.2039 2.6443 E
 SED: Overall Standard Error of Difference 2.762

 ---- ---- ---- ---- ---- ---- ---- ---- 2 ---- ---- ---- ---- ---- ----
---- ----
 Env is averaged of combinations present in data
 Predicted values of tch
 Gen is ignored in the prediction (except
where specifically included
 Cclass is ignored in the prediction (except
where specifically included

 LocGroup Predicted_Value Standard_Error Ecode
            2 87.8125 2.5234 E
            1 85.2039 3.5312 E
 SED: Overall Standard Error of Difference 3.238

Note carefully the commentary immediately before each set of predictions.

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 Wed Nov 03 2004 - 13:45:59 EST