Hi there
The manual points out that after running xtlogit with random effects, one
should use quadchck (though I don't see why this isn't just the default in
xtlogit). This is because the quadrature method of computing the log
likelihood and the derivatives may give unstable estimates. This makes
sense.
Rather cryptically the manual (version 7.0) also says in the 'quadchck'
entry "Some random-effects estimators in Stata use Gauss-Hermite
quadrature...).
My questions are:
1. Which estimators do and which don't use G-H quadrature?
2. Or, if #1 is too much to answer, what does xtnbreg use?
3. How can we check for 'stability' with whatever other methods are used?
4. If Stata does use different optimization methods for different
estimators, what determines which algorithm is chosen?
5. And how about making (perhaps a non-noisy) quadchck a default for those
xt family members that need it?
Thanks!
Alex Cowell
Alex Cowell, Ph.D.
Behavioral Health Economics Program
RTI
3040 Cornwallis Road PHONE:
919.541.8754
PO Box 12194 FAX:
919. 541.6683
Research Triangle Park E-MAIL:
[email protected]
North Carolina 27709-2194
*
* 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/
