st: -xtlogit- : rnd fx model fails to converge?

[Jason Thompson <jat@northwestern.edu>]

Why might a random-effects model with about 20 covariates run with 
-xtlogit, i(panelvar)- on about 135,000 observations divided across 125 
panels churn for 300+ iterations without returning either a result or an 
error? Finagling the quadrature parameter doesn't seem to have an effect. 
However, -xtlogit- successfully estimates a model using a few fewer 
variables in about 10 iterations. Am I possibly coming up against some 
limit in terms of the number of allowable covariates? Any other insights?


*
*   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/