Upon further reflection, it's dawned on me that the ado file I posted
yesterday doesn't do what was intended, and doesn't even do anything
interesting. If there is a way in which Level-2 variances can be separately
estimated for noncross-classified factors in a single model with
either -xtmixed- or -gllamm-, then it isn't obvious to me. Perhaps one of
the structural equation modeling packages that Stas mentioned would be the
way.
Joseph Coveney
*
* 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/
