I have a two stage model: random effects panel in the
first stage and a fixed effects panel in the second
stage with predicted probabilities from the first
stage. Both models are unbalanced panels with
different number of observations in each stage. I run
a bootstrap in the second stage but get a message
"insufficient observations to compute bootstrap
standard errors
no results will be saved." The model does not
converge. The code works as I have used it with a
balanced panel. Is it possible that this is happening
because the data set contains all observations (some
are used in the first stage but may not be used in the
second stage do to missing values for some variables)?
Does anyone know how could I achieve convergence in
this case?
Martina Vidovic
Assistant Professor
Department of Economics
Bloomsburg University
400 East Second Street
Bloomsburg PA, 17815
Phone: 570-389-4737
Fax: 570-389-4338
__________________________________
Yahoo! Mail - PC Magazine Editors' Choice 2005
http://mail.yahoo.com
*
* 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/
