Re: GLMM analysis in asreml

From: <arthur.gilmour_at_DPI.NSW.GOV.AU>
Date: Thu, 26 Jun 2008 11:12:14 +1000

Dear Ian,


Consider threshold model with single random effect plus error.
On underlying scale, total variance is say B + W and intraclass
correlation is B/(B + W).

Let R = B/W. Total variance is W(1+R) and correlation is R/(1+R). For
probit W = 1, for logit W = pi^2/3, etc.

In asreml output, the same number appears in variance ratio and
component columns. Is this R or B = RW ?

The variance component for the random factor is B.
The 'residual variance' under the GLMM model is actually as dispersion
factor in the sense that it is
a scaling multiplier applied to the glm variance/weight. It can be
'floated' to the variance of the working variable with !DISP
or fixed to a set value (say 0.9) with !DISP 0.9

Some examples have been drafted for the ASReml 3 User Guide.

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:
Towoomba (MFX) 19-23 May
Melbourne Aust Stat Soc 3rd July
Argentina 9-19 September ASReml WS + Biometrics 
Received on Sat Jun 26 2008 - 11:12:14 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.)