[R] Problem with nlme package

Bill.Venables at csiro.au Bill.Venables at csiro.au
Wed Nov 17 23:22:37 CET 2010

The function is not exported from the package.  You have to get tough with it, e.g.

> library(nlme)
> summary.lme
Error: object 'summary.lme' not found

But if you insist:

> nlme:::summary.lme
function (object, adjustSigma = TRUE, verbose = FALSE, ...) 
    fixed <- fixef(object)

You cannot do this with lme4 since there the methods are S4 rather than S3 (which is why it has a 4 in the name, I suspect, like the stats4 package).

Also, tucked away in the 'ape' package there is a function varcomp() which extracts variance components from lme objects.  This is all I have ever needed in addition to what is provided in nlme directly.

Bill V.

-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Joanna Geller
Sent: Thursday, 18 November 2010 8:07 AM
To: David Winsemius
Cc: r-help at r-project.org
Subject: Re: [R] Problem with nlme package

Thanks for the suggestions - I tried all of them, including
require(lme4) and require(nlme) and summary.lme still cannot be found.
I want to use it to get full output of a multi-level model. Maybe it's
a Mac thing?

Any other suggestions would be much appreciated! Thanks, again.

On Wed, Nov 17, 2010 at 3:51 PM, David Winsemius <dwinsemius at comcast.net> wrote:
> On Nov 17, 2010, at 4:48 PM, David Winsemius wrote:
>> On Nov 17, 2010, at 4:39 PM, Joanna Geller wrote:
>>> Hello,
>>> I have installed the nlme package, but every time I try to use the
>>> function "summary.lme,"
>> How did you "try to use it"?
>>> I get a message that the function cannot be
>>> found.
>> If it says it cannot be found, then you quite possibly forgot to load the
>> "lme4" package.
> (or the nlme package)
> Try:
> require(nlme)
> --
> David Winsemius, MD
> West Hartford, CT

R-help at r-project.org mailing list
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list