I would imagine that the set of equations is not solvable because of being
underidentified.
For example, how can you separate the effect of y1 on y2 from the effect
of y2 on y1?
Tim
Kelvin Foo <kelvinski@gmail.com>
Sent by: owner-statalist@hsphsun2.harvard.edu
11/07/2006 12:20
Please respond to
statalist@hsphsun2.harvard.edu
To
statalist@hsphsun2.harvard.edu
cc
Subject
st: Simultaneous eqns containing endogenous binary var
Dear All,
I would like to find the estimates for these 3 simultaneous equations:
Eqn 1: y1 = f(y2, y3, X1)
Eqn 2: y2 = f(y1, y3, X2)
Eqn 3: y3 = f(y1, y2, X3)
y3: endogenous binary variable,
y1, y2: endogenous continuous variables, and
X1, X2, X3: sets of exogenous variables.
If it helps, let's assume that all disturbance terms are independent
and normally distributed.
Taken separately, I could estimate Eqns 1 and 2 using -regress-, and
Eqn 3 using -probit-. However, I am not sure how to proceed if these
were to be seen as a system of simultaneous equations. Is there a
command for this in Stata 9? Any other comments/suggestions would be
greatly appreciated too.
Thanks in advance!
Kelvin
*
* 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/
*
* 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/