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: Re: Quadratic Instrumental Variables


From   Christopher Baum <kit.baum@bc.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   re:st: Re: Quadratic Instrumental Variables
Date   Mon, 2 Jan 2012 12:37:29 -0500

<>
Is it possible to use quadratic instrumental variables on Stata using
  ivregress command?

fertility = a0 +a1 x education + a2 x ...+ u

education is endogenous so i will use distance to Tehran and square  
distance to Tehran as instruments. The reduced form equation:

education = b0 + b1x distance to Tehran + b2 x (distance to Tehran)^2




This is not 'nonlinear IV' in any sense. If distance is exogenous (as it obviously is) then
including it and any nonlinear function of it is perfectly straightforward IV. You're just
saying that education is a curvilinear function of distance to the capital (and whatever
included exogenous factors appear in the main equation).

To get a broader set of diagnostics for your IV model, you might want to use Baum-Schaffer-Stillman's
-ivreg2-, latest version on SSC, documented extensively in Stata J 2003, 2007 (free downloads).

Kit


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/


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