Dear Ian,
Indeed it should work.
If you have a simple example that doesn't work, I'm happy to check it out
in case I can find a bug. It could be that the combination fails
but if so, I want to fix it.
Arthur
> From: Ian White <imsw@holyrood.ed.ac.uk>
> To: gilmoua@agric.nsw.gov.au
> Subject: asreml (more on !F)
>
> Dear Arthur,
>
> Suppose I want to associate a G-inverse matrix with a set of covariates
> Z1...Zn. I thought that one way to do this would be to read them
> into the program as a 'factor' ZFAC:
>
> ZFAC n !F
>
> Then I could have Y ~ ... !r giv(ZFAC) ... to associate an n x n matrix
> in zfac.giv say with the covariates. Should this work? I have tried it
> with some simple examples, sometimes it seems to work, other times it
> doesn't -- giving zero blups for the giv(ZFAC) terms.
>
> Regards,
> Ian
>
>
> ************************************************
> * I.White *
> * ICAPB, University of Edinburgh *
> * Ashworth Laboratories, West Mains Road *
> * Edinburgh EH9 3JT *
> * Fax: 0131 667 3210 Tel: 0131 650 5490 *
> * E-mail: i.m.s.white@ed.ac.uk *
> ************************************************
>