R help - Apr 2009 - lme between-group and within-group covariance

Dear R users,

I would be interested in using the lme() function to fit a linear mixed
model to a longitudinal dataset. I know this function allows for the
specification of a within-group covariance structure. However, does it allow
for the explicit specification of a between-group covariance structure?

Being able to specify both separately would be very important in the context
of my project since, as might be expected, they have different
implications/interpretations.

For instance, the mixed procedure in SAS allows users to specify the two
structures separately by adding a value for the type argument after the
RANDOM statement and the REPEATED statement.

My question is thus if we can do the same with lme().

I thank you most sincerely for your help.     
-- 
View this message in context:
http://www.nabble.com/lme-between-group-and-within-group-covariance-tp22834748p22834748.html
Sent from the R help mailing list archive at Nabble.com.

I will try to make this more precise. In the lme() function, the
"correlation" argument allows the user to specify a within-group
correlation
structure, i.e. the structure of the Lambda matrix using the mixed model
notation in Pineiro and Bates. What I want to do is specify a distinct
structure for the Psi matrix (same notation), that is, a correlation
structure for the random effects.

If lme() doesn't allow for this, is there any other function that I could
use?



MUHC-Research wrote:
> 
> Dear R users,
> 
> I would be interested in using the lme() function to fit a linear mixed
> model to a longitudinal dataset. I know this function allows for the
> specification of a within-group covariance structure. However, does it
> allow for the explicit specification of a between-group covariance
> structure?
> 
> Being able to specify both separately would be very important in the
> context of my project since, as might be expected, they have different
> implications/interpretations.
> 
> For instance, the mixed procedure in SAS allows users to specify the two
> structures separately by adding a value for the type argument after the
> RANDOM statement and the REPEATED statement.
> 
> My question is thus if we can do the same with lme().
> 
> I thank you most sincerely for your help.     
> 
-- 
View this message in context:
http://www.nabble.com/lme-between-group-and-within-group-covariance-tp22834748p22868945.html
Sent from the R help mailing list archive at Nabble.com.