stata needs a mixed-models routine to remain competitive (for some
users) against SAS and even SPSS.
Incorporating gllamm into the main stata code may be one way forward,
but there are others. Some multilevel texts (eg Snijders & Bosker
2002) note the usefulness of the xt commands for models with random
intercepts. Extending the xt series, if possible (a big if), might
provide a simpler set of commands for some existing users to run mixed
models than learning the more fully featured gllamm.
Benchmarks of gllamm against SAS/HLM/MLwin/R-nlme for standard mixed
models -- whilst in some senses unfair -- would make stata appear
extremely slow.
----------------------
Stephen McKay
PFRC, School of Geographical Sciences
University of Bristol
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
