Re: singularities appeared in AI matrix

From: Arthur <asremlforum_at_VSNI.CO.UK>
Date: Fri, 11 Sep 2009 09:07:03 +0100

Dear Ineke,

Brian's comments are right.

Under a sire model, it is possible for the intraclass correlation to exceed 0.25 implying a heritability greater than 1. When that happens, ASReml would fail
to fit an animal model because h2 > 1 implies residual variance is negative.

This can happen if there are fixed effects confounded with sire effects,
and for some data structures, when there are maternal effects and/or
family effects. Since your data is a four level discrete scale, this could be contributing to the problem as well.

------------------------
Arthur Gilmour

Retired Principal Research Scientist (Biometrics)

-------------------- m2f --------------------

Sent using Mail2Forum (http://www.mail2forum.com).

Read this topic online here:
http://www.vsni.co.uk/forum/viewtopic.php?p=833#833

-------------------- m2f --------------------
Received on Sat Sep 11 2009 - 09:07:03 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.)