From: <arthur.gilmour_at_DPI.NSW.GOV.AU>
Date: Tue, 8 Apr 2008 11:09:43 +1000

Dear Jo,

We have an xfa MET model with two predict lines:
predict Trial Clone !onlyuse xfa(Trial,1).Clone
predict Trial Clone
In the pvs file the 2 overall standard error of the difference values we
obtain are:
My question is why are these 2 values not equal to the average of the
individual values which are .47 and .51?

I'm not sure where you are getting the last two numbers from. I would
have expected the average value
reported obtained after using the !SED qualifier to be much closer
although not necessarily equal to that
reported when !SED is not specified. The difference is that the default
average SED is calculated
from the average variance and covariance while the average of the SED's
reported with !SED
is the average of the actual SED values. So there is a different
weighting, particularly if variances and
covariances are variable.

But I note that the two SEDs you have mentioned above are about SQRT(2)
bigger than 'individual values'
so are these individual values in fact just the average standard errors,
and not average SED's.

I would need to see the job to comment any further.

May Jesus Christ be gracious to you in 2008,

Arthur Gilmour, His servant .
Mixed model regression mapping for QTL detection in experimental crosses.
Computational Statistics and Data Analysis 51:3749-3764 at

Personal website:

Skype: arthur.gilmour,
Principal Research Scientist (Biometrics)
NSW Department of Primary Industries
Orange Agricultural Institute, Forest Rd, ORANGE, 2800, AUSTRALIA
fax: 02 6391 3899; 02 6391 3922 Australia +61
telephone work: 02 6391 3815; home: 02 6364 3288; mobile: 0438 251 426

ASREML 2 is now available from
The ASReml discussion group is at
To join it,
Archives are at

The ASReml3 alpha download registration page is:
There are asreml3alpha forums at:

Proposed travel:
Argentina 9-19 September ASReml WS + Biometrics 
Received on Thu Apr 08 2008 - 11:09:43 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.)