> -----Original Message-----
> From: Franz Mueter [mailto:fmueter@sfu.ca]
> Sent: Thursday, 21 December 2000 11:21
> To: s-news@wubios.wustl.edu
> Subject: [S] LME model with random effect that depends on continuous
> covariate
>
> I would like to fit a random effects model where the random effect is
> assumed to vary linearly with a covariate rather than having
> a constant mean within a group or groups.
> Can such a model be implemented using lme or can anyone
> suggest appropriate function/software to implement such
> a model? Thank you, Franz
Eh?? I don't get it.
If a random effect varies linearly with a covariate it is not random.
If the mean of a random effect varies linearly with a covariate the mean can
be subsumed into the fixed part of the model and the random effect can,
without loss of generality, be assumed to have mean zero.
Bill Venables.
--
Bill Venables, CSIRO/CMIS Environmetrics Project
Email: Bill.Venables@cmis.csiro.au
Phone: +61 7 3826 7251
Fax: +61 7 3826 7304
Postal: PO Box 120, Cleveland, Qld 4163, AUSTRALIA
"Natum videte, regem angelorum. Venite adoremus!"
|