Dear Statalist,
I am estimating a cross-sectional probit model with clusters. I need to
disentangle the estimated coefficients - I have eight coefficients and
need to recover eight different parameters from the estimates. To make
my problem more clear, here is a simplified example:
Let's say my estimated coefficients are alpha, beta, and gamma, and the
parameters I need to recover are a, b, and c. The following
equalities hold:
alpha=a*b
beta=c*a-b+5
gamma=a*c*(2+a).
Since the parameters I need enter several of the coefficients, I don't
think I can use the delta method. However, it seems that I could use
Chamberlain's minimum distance estimator.
Does anybody know how to do this in Stata? I am using Stata 8.2.
I searched the usual ways, and all I found was a question to the Statalist
from 2003 about this estimator for panel-data, which was not answered.
Any help would be greatly appreciated.
Thanks a lot,
Kristin
Kristin J. Kleinjans
University of Aarhus
Department of Economics
E-mail: kkleinjans@econ.au.dk
Website: www.econ.au.dk/vip_htm/kkleinjans/Default.htm
*
* 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/