st: SAS PROC GLIMMIX vs. Stata generalized linear mixed model commands

[Stas Kolenikov <skolenik@gmail.com>]

Folks,

Does anybody know about the best way to match up what SAS and Stata do
in terms of multilevel / mixed models? Lesa Hoffman from U of
Nebraska, Lincoln, has been able to find a matching pair of options
(http://psych.unl.edu/hoffman/Sheets/Workshops/ICPSR4_Example10b_Generalized_Clustered_Models.pdf)
for Gauss-Hermite quadrature with a fixed number of integration
points:

SAS:

PROC GLIMMIX DATA=... METHOD = QUAD (QPOINTS=7);
 CLASS ... ;
 MODEL response = predictors  / SOLUTION LINK=LOGIT  DIST=BIN DDFM=BW;
 RANDOM INTERCEPT / TYPE=UN  SUBJECT = cluster;
RUN;

Stata:

xtmelogit response predictors, || cluster: , variance
covariance(unstructured) intpoints(7)

Are there any other estimation methods for generalized linear mixed
models (in particular, mixed/multilevel logistic model) that these two
packages have in common?

-- Stas Kolenikov, PhD, PStat (ASA, SSC)
-- Principal Survey Scientist, Abt SRBI
-- Opinions stated in this email are mine only, and do not reflect the
position of my employer
-- http://stas.kolenikov.name
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/