Re:fitting random regressions
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re:fitting random regressions

> I would try the model
> height ~ ... fixed effects ... !r block tree.pol(age,2) ...
> 0 0 1
> tree.pol(age,2)
> tree 0 0
> 3 0 US ...six initial values... !GP
I tried this and something similar before, but because I have several
(10) records for the same individual (each one with the assessment for
an specific age)  I receive an error getting the pedigree.  The error is
in some way logical because of the repeated individual codes, but I
tried with !ASMV 10 without positive results.  Furthermore, with that
approach I'm not modelling the  error structure.

> It may not be appropriate to suggest this
> on an ASREML discussion group, but you may
> find it easier to approach this analysis using
> the new version of DFREML, which includes
> a program to do estimation of Covariance
> Functions. Sorry Arthur.
Actually, Karin Meyer's program fits only one random term. It is also
limited to orthogonal polynomials and I would like to try with splines
later.  I simplified the presentation of the problem, but I have more
than just block and tree as random terms in the model.

I would be very grateful about other suggestions and thanks for your


Luis Apiolaza
Institute of Veterinary, Animal and Biomedical Sciences
Massey University
Palmerston North
New Zealand

"Quote me as saying I was misquoted " - Groucho Marx