Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

st: Instrumental Variables: discrete endogenous & continuous outcome


From   Phanwin Yokying <yadawe@hotmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Instrumental Variables: discrete endogenous & continuous outcome
Date   Mon, 1 Apr 2013 11:49:45 -0400

Dear Statalisters,

      I am running a regression with several binary endogenous variables and a continuous outcome using the IV approach. 

  Y = aX1 + bX2 +  c X3+ dX2*X1 +eX2*X3 + controls 
,where
Y is continuous
X1 is discrete exogenous variable (demographic characteristics)
X2 is discrete endogenous variable 
X3 is discrete exogenous variables (e.g demographic characteristics) 

Y also suffers from selection bias, which implies that Heckman selection bias method might be necessary also.

Question1: If I were to run this "by hand," what steps would you suggest I should take? I have taken the following steps:
1. X2 = Z + controls
2. predict ghat
3. ivregress = controls (X2 = ghat) >>>> how do I incorporate the interaction terms and correction bias here? Could you advice?

Question 2: ivregress gmm Y controls (X2 X2*X1 = Z Z*X1)  >>> would this be the correct way to approach this? how can I take into consideration the selection bias that exists in Y? 

Your help and advise would be much appreciated. 



*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index