[R] glmmPQL in 2.3.1

[Christian Gold]

I have come across the previous communication on this list in September 
(copied below) because I had received the same error message.

I understand from Brian Ripley's reply that anova should not be used 
with glmmPQL because it is not an adequate method, and that this is now 
shown with an error message.
My question is, what method *should* be used? Using summary does not 
give me the result I want, because it shows the significance of each 
combination of factor *levels*, rather than factors, which can quickly 
become very hard to interpret.

Many thanks for your input!

Christian Gold
http://www.uib.no/people/cgo022/




Re: [R] glmmPQL in 2.3.1
This message: [ Message body ] [ More options ]
Related messages: [ Next message ] [ Previous message ] [ In reply to ] 
[ [R] glmmPQL in 2.3.1 ]
From: Prof Brian Ripley <ripley_at_stats.ox.ac.uk>
Date: Tue 26 Sep 2006 - 09:58:19 GMT


On Mon, 25 Sep 2006, Justin Rhodes wrote:

 > Dear R-help,
 >
 > I recently tried implementing glmmPQL in 2.3.1,

I thought *I* had implemented it: are you talking about my function in 
package MASS or your own implementation?

 > and I discovered a few differences as compared to 2.2.1.

You appear to be talking about contributed packages (MASS, and glmmPQL 
also depends on nlme) without giving their version numbers.

 > I am fitting a regression with fixed and random effects with Gamma error
 > structure. First, 2.3.1 gives different estimates than 2.2.1, and
 > 2.3.1, takes more iterations to converge.

We have no idea, given the lack of reproducible example. glmmPQL does 
give the same answers as before for the book examples for which it is 
support software. This may well be due to an underlying change in nlme.

 > Second, when I try using the anova function it says, "'anova' is not
 > available for PQL fits", why? Any help would be greatly appreciated.

Because anova implies you are using an optimization criterion, such as 
least squares or maximum likelihood, and so there is something like a 
deviance to partition. It was not used in the book with glmmPQL 
supports, but it seems some people were using glmmPQL without reference 
to that book so I made a number of their misuses explicit errors. This 
*is* in the NEWS and WHATS.NEWS files for MASS and VR:
There are anova() and logLik() methods for class "glmmPQL" to stop misuse.
--