[R] zero random effect sizes with binomial lmer

Andrew Robinson A.Robinson at ms.unimelb.edu.au
Tue Jan 2 03:14:30 CET 2007

Good observation, Daniel.  I had not picked up the different default
fitting method. 



On Mon, Jan 01, 2007 at 08:59:55PM -0500, Daniel Ezra Johnson wrote:
> > From: Andrew Robinson <A.Robinson_at_ms.unimelb.edu.au>
> > Date: Mon 01 Jan 2007 - 19:19:29 GMT
> >
> > I tried an earlier version of R, on a different platform, and got quite 
> > different results. Sadly, the *earlier* results are the ones that make 
> > sense.
> Andrew, I tried installing R 2.3.1, it seemed to work as you said, but I 
> realized it was because the default method was PQL instead of Laplace. 
> Switching the method to Laplace, the zero effect came back.
> It seems like there's no easy way around this. I would like to compare 
> random effect sizes between different subsets of my data, but this may not 
> be possible using the current functions...
> Daniel
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

Andrew Robinson  
Department of Mathematics and Statistics            Tel: +61-3-8344-9763
University of Melbourne, VIC 3010 Australia         Fax: +61-3-8344-4599

More information about the R-help mailing list