Hi,
I want to estimate a simultaneous model with panel data using 2sls.
The model is as follows (I have omitted time and individual
subscripts, as well as errors):
y1= a + bx1 +bx2 + ... + by2
y2= c + bz1 +bz2 + ... + by1
This would be the kind of model for which one would use -reg3- if
we were talking about cross section data.
Now, the problem is that if I estimate each equation separately,
using the two-stage procedure, estimates will be inefficient when
compared to the system estimates.
Does anybody have any ideas as to how I might solve the problem?
I would appreciate any insights you may have.
Thanks in advance,
Alvaro
*
* 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/
