[R-sig-ME] Interesting software comparison paper
Viechtbauer Wolfgang (STAT)
Wolfgang.Viechtbauer at STAT.unimaas.nl
Tue May 25 11:19:31 CEST 2010
I just stumbled across this article and I figured this may be of interest to some of you:
Austin, P. C. (2010). Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures. The International Journal of Biostatistics, 6(1).
At least, the issue of what to do when the number of clusters is low has come up several times before on this list.
The comparison includes glmmPQL and glmer (although I suspect the version of glmer used was quite old; the author does not mention the version number of the lme4 package used, but does mention using R 2.8.0 -- which is a bit dated). Nice to see that glmer compares very well with other software.
Wolfgang Viechtbauer http://www.wvbauer.com/
Department of Methodology and Statistics Tel: +31 (43) 388-2277
School for Public Health and Primary Care Office Location:
Maastricht University, P.O. Box 616 Room B2.01 (second floor)
6200 MD Maastricht, The Netherlands Debyeplein 1 (Randwyck)
More information about the R-sig-mixed-models