Does anyone know of a good HLM6 to Stata 10 comparison for estimating
multilevel models? I assume both have strengths and weaknesses - a
side-by-side comparison would be very helpful to me.
I have Rabe-Hesketh & Skrondal's excellent book, Multilevel and
Longitudinal Modeling Using Stata (2nd ed.). For the past few weeks,
I've been running models in both HLM and Stata during a graduate
multilevel modeling course and comparing the output. (Running models
in Stata is just for my benefit and is not part of the course.) The
estimates from unconditional models in HLM and xtreg are similar but
not identical. The differences are generally small when the same
method is used (e.g., GLS, ML). Is it safe to assume that the
differences are due to slightly differing algorithms between the two
software packages?
Obviously, I'm doing coursework in HLM, the package used during the
course. But in general, I'd like to avoid using HLM in the future, if
for no other reason than the lack of support for OS X.
Troy Payne
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
