xt iv regression: instrumented variables with different instruments

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

xt iv regression: instrumented variables with different instruments

nicolas87
This post has NOT been accepted by the mailing list yet.
Hey statalist,

I want to estimate a unbalanced panel. My problem is that I have two variables that I need to instrument but I want to use a different instrument for each one. Is there a command that solves my problem?

Reply | Threaded
Open this post in threaded view
|

Re: xt iv regression: instrumented variables with different instruments

nicolas87
This post has NOT been accepted by the mailing list yet.
Thank you very much for your reply and the link to kit Baum his answer!

my regression could be presented like this:

= equals "is function from"

y1= x1 x2 y2 y3 + e
y2 = x4 x5 x6  y3 +u
y3 = x7 x8 x9 y2 +v
x4= x7 +error
x5=x8 +error
x6=x9 +error

Because E[x4-x9 , e]= 0

ivreg29 y1 x1 x2  (y2 y3= x4-x9),...

Correct?