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]

st: endogen indicator variable


From   "Ralph Ehrensperger" <s0771939@access.uzh.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: endogen indicator variable
Date   Wed, 24 Jul 2013 17:07:55 +0200

Dear Statalist users

I would like to instrument my endogen indicator variable A with the
instrument Z. I have panel data and all variables are quantitative, only my
endogen repressor A and the instrument Z are binary (0, 1). My model looks
as follows:

y = b0 + b1 x1 + b2 x1 A + b3 x1 x3
If I generate the indicator like: quietly generate x1A = x1*A, I don't know
how I could then integrate my instrument Z instead of A. (The control
variable x3 should not be a problem, gen x1x3 = x1*x3)


I guess doing 2SLS by hand, e.g. 
first ivreg y = b0 + b1x1 + b2` (A=Z) + b3 x1x3 and then just take this b2`
into the regression:
Quietly gen AZ= b2`* Z * x1 and then do the panel regression:
Xtreg y x1 AZ x1x3 
would be incorrect due to the residuals?! (Baum 2006, p. 189)


Thank you very much in advance for your help!
Kind regards
Ralph Ehrensperger


*
*   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