Namho Kwon,

In STATA 1you have several commands available.  The simplest is a basic two stage least squared command: ivreg.  You can do the same thing, but you have more options with ivregress.

You can estimate more complex multi-equation models using reg3.  

As an aside, it looks like one of the exclusions you are making to get the equations to estimate are of x_2 in equation 1 and x_1*x_2 in equation 2.  The problem with this strategy is that in most circumstances it isn't proper to omit one of the constitutive terms when you include an interaction term.  This might just be a typo. 

Jesse Richman
Assistant Professor
Old Dominion University 

-----Original Message-----
From: Political Methodology Society [mailto:[log in to unmask]] On Behalf Of Namho Kwon
Sent: Tuesday, September 29, 2009 1:21 PM
To: [log in to unmask]
Subject: [POLMETH] Simultaneous Equation in SAS and Stata

How are you?

I am dealing with some simutaneous equations with SAS and STATA.
My eqs are like this;

first equation:        y = b_0 + b_1*x_1 + b_2*(x_1*x_2) + x_3 + e
secon equation: x_1 = a_0 + a_2*x_2 + a_3*y + r

As you can see,  x_1 (dependent var of 2nd equation) appears on the 1st
equation as an independent var.
Also, y (dependent var of 1st equatino) appears on the 2nd equation as an
independent var.
There is a cross term of x_1*x_2 on the 1st equation. x_2 appears on both
equations.

For SAS, I think I have to use "proc syslin". I am not sure the EXACT
commands(programming) for this.
For STATA, "ivregress" or "reg3" should be used, I think. I don't still get
them 100% sure.

Could you give me some advices? Thank you.


-- 
Namho Kwon
Master of Science in Public Policy and Management, 2010
Heinz College of Public Policy and Management
Carnegie Mellon University

**********************************************************
             Political Methodology E-Mail List
   Editors: Xun Pang        <[log in to unmask]>
            Jon C. Rogowski <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************

**********************************************************
             Political Methodology E-Mail List
   Editors: Xun Pang        <[log in to unmask]>
            Jon C. Rogowski <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************