s-news
[Top] [All Lists]

Re: vcov function with lme object

To: Achaz Graf Von Hardenberg <achaz.von.hardenberg@usherbrooke.ca>
Subject: Re: vcov function with lme object
From: Prof Brian Ripley <ripley@stats.ox.ac.uk>
Date: Thu, 11 Nov 2004 11:07:43 +0000 (GMT)
Cc: <s-news@lists.biostat.wustl.edu>
In-reply-to: <1100170679.419345b722c7b@www.usherbrooke.ca>
On Thu, 11 Nov 2004, Achaz Graf Von Hardenberg wrote:

> Hi,
> I would like to obtain the variance-covariance matrix for an lme object and
> terefore tried the following:
>
> >library(MASS)
> >x<- vcov(myobject.lme)
>
> however, I get the following error message:
>
> Error in UseMethod("vcov"): no specific or default method found
>
> What am I doing wrong?

Not telling us the version of S-PLUS and of MASS for a start.
Here is an example from S-PLUS 6.2 and the current MASS version 7.1pl021

> fm1 <- lme(distance ~ age, data=Orthodont) # random is ~ age
> vcov(fm1)
            (Intercept)          age
(Intercept)  0.60100669 -0.046850866
        age -0.04685087  0.005077029

-- 
Brian D. Ripley,                  ripley@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595


<Prev in Thread] Current Thread [Next in Thread>