Further to my posting yesterday I think I have figured this out to my
satisfaction when I compare with SAS output.
The hat elements are the diagonals of WC(superscript: -1)W', the variances of
predicted values. So to get var(ehat)/var(e) one needs to divide the hat value
by the residual variance and multiply by the weight (for a weighted analysis)
before subtracting from 1.
I think this is probably what is intended on page 127 of the manual.
DLJ
___________________________________________________________________________
THE FOLLOWING WARNINGS ATTACH TO THIS COMMUNICATION
This material is intended for the named recipient only and has been created
solely for the purpose and function of Livestock Improvement Corporation Limited
and may contain information that is subject to the Privacy Act / Confidentiality
/ Privilege / Copyright. Any person other than the named recipient is prohibited
from retaining / disclosing / copying / distributing / using all or part of this
material.
--
Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml