R help - Oct 2006 - Nonlinear mixed effects model

In nonlinear mixed effects models, SAS doesn't allow for free manipulation
of
the covariance matrix (you can only specify a "type", and our
"type" doesn't
exist). Can R accomplish this? For example:

Parameters:
B1= Beta 1i
B2= Beta 2i
G1= Gamma i


y = B1 -(B1 - B2) exp { - G1 time} + e

the covariance matrix for 
(B1         [( covB1?     covB1B2   covB1G1
 B2    ~      covB2B1    covB2?     covB2G1
 G1)           covG1B1   covG1B2   covG1?   )]

**If we want to specify covG1B1 and make everything else 0's, for example,
what would the code look like? 



Thanks for your time.
-- 
View this message in context:
http://www.nabble.com/Nonlinear-mixed-effects-model-tf2397889.html#a6686679
Sent from the R help mailing list archive at Nabble.com.

Have you read Pinheiro and Bates (2000) Mixed-Effects Models in S 
and S-Plus (Springer), especially the discussion of 'corStruct' classes 
in ch. 5 and the nonlinear mixed-effects models in Part II?  Bates has 
kept a small army of graduate students busy for over 20 years developing 
good ways to do things like this, and this book is probably the 
best-known product of that work. 

      Hope this helps. 
      Spencer Graves

Cam wrote:
> In nonlinear mixed effects models, SAS doesn't allow for free
manipulation of
> the covariance matrix (you can only specify a "type", and our
"type" doesn't
> exist). Can R accomplish this? For example:
>
> Parameters:
> B1= Beta 1i
> B2= Beta 2i
> G1= Gamma i
>
>
> y = B1 -(B1 - B2) exp { - G1 time} + e
>
> the covariance matrix for 
> (B1         [( covB1?     covB1B2   covB1G1
>  B2    ~      covB2B1    covB2?     covB2G1
>  G1)           covG1B1   covG1B2   covG1?   )]
>
> **If we want to specify covG1B1 and make everything else 0's, for
example,
> what would the code look like? 
>
>
>
> Thanks for your time.
>