Re: st: ivreg2: interacting the endogenous regressor

[Christopher Baum <kit.baum@bc.edu>]

<>
On May 23, 2012, at 8:33 AM, Jana wrote:

> I need to interact my endogenous variable (for which I'm  
> instrumenting) with one of the exogenous variables in my step2  
> equation. Is there a straightforward way to do this using ivreg2? I'm  
> reluctant to do it by hand because I'm not certain whether the  
> standard errors would be right; I am also a bit of a novice on iv  
> regression and so would like to be able to take advantage of ivreg2's  
> already-programmed post-estimation tests, etc.

You need an additional instrument to do that: if you have y2 and x1*y2 in the regression (y endog, x exog) you need to form the instruiments
(z1 z1*x1), where z1 is the excluded instrument. If z1 is an appropriate instrument, and x1 is truly exogenous, then the product of z1*x1 will also be 
exogenous.

Go Blue!

Kit Baum
co-author ivreg2


Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                             An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
  An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/