[R] Fwd: How to sample from a linear mixed model

[Douglas Bates]

I forgot to cc: R-help on this reply.

---------- Forwarded message ----------
From: Douglas Bates <dmbates at gmail.com>
Date: Jun 19, 2005 7:55 PM
Subject: Re: [R] How to sample from a linear mixed model
To: Søren Højsgaard <Soren.Hojsgaard at agrsci.dk>


On 6/19/05, Søren Højsgaard <Soren.Hojsgaard at agrsci.dk> wrote:
> I would like to draw a sample from a linear mixed model y=Xb+Zu+e which has been fitted with lme(), i.e. a model y ~ N(Xb, C), where C=Z cov(u) Z' + cov(e).
> I've tried to figure out how to extract C from an lme object, because that would solve my problem when also using the predict() function, but without any luck.
> Can anyone help on that?

C is not stored in an lme object.  In fact it is never created.
(Consider the dimensions of this matrix.  It could be huge.)

The easiest way to simulate data from a linear mixed model is to
simulate u and e then form Xb+Zu+e