Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: IV: endogenous interaction regressor and interaction instrument


From   Austin Nichols <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: IV: endogenous interaction regressor and interaction instrument
Date   Mon, 25 Nov 2013 12:33:55 -0500

Olivia Bertelli <[email protected]>:

gen Z1xZ2=Z1*Z2
gen X1xZ2=X1*Z2
ssc inst ivreg2
ivreg2 Y Z2 (X1 X1xZ2=Z1 Z1xZ2)


On Fri, Nov 22, 2013 at 11:03 AM, Olivia Bertelli
<[email protected]> wrote:
> Dear Statalists,
>
> I want to estimate the following regression with an IV 2SLS method,
> having two endogenous regressors:
>
> 1st stage:
>
> X1 = b1*Z1 + b2*(Z1 x Z2)
>
> and
>
> X1 x Z2 = b1*Z1 + b2*(Z1 x Z2)
>
> where, Z1 and Z1 x Z2 are the excluded instruments, X1 is endogenous,
> and both X1 x Z2 and Z1 x Z2 are interaction terms
>
> 2nd stage:
>
> Y = a1*X1 + a2 *(X1 x Z2)
>
> My question is: how to I handle endogenous interaction terms
> instrumented with exogenous interactions? should I include also a3*Z2
> alone in the 2nd stage? Or rather in the first stage? Neither of the
> two?
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index