Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: simple question on 2SLS??


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: simple question on 2SLS??
Date   Tue, 30 May 2006 22:44:39 +0100

Kris,

Your questions are common ones that come up on the list from time to
time; see below.

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Kristopher Dawsey
> Sent: 30 May 2006 22:25
> To: statalist@hsphsun2.harvard.edu
> Subject: st: simple question on 2SLS??
> 
> Hello all,
>     I'm a beginner at Stata, and not much of a pro in 
> econometrics either.  I am trying to reproduce the results of 
> a paper on FDI and economic growth.  They have the following 
> structural equation,
>  
>     growth = a + b*FDI + c*FDI*education + d*other_things ... + error
>  
> where FDI is thought to be endogenous.  So you can see that 
> the endogenous variable is interacted with an exogenous 
> variable in the structural equation.  My question is how to 
> force Stata to do this with ivreg?  I could not figure out 
> how to get this idea into the command line.

You have to create your own instruments for the FDI*education variable.
The natural thing to do is to interact education with the excluded
instruments.  See e.g.

http://www.stata.com/statalist/archive/2004-08/msg00780.html

> Another question is that ivreg seems to automatically use all 
> exogenous variables in the first stage, how can i force it to 
> use only the instruments I specify?

You *don't* want to do this.  There is a Stata FAQ on it plus regular
postings to Statalist, e.g.

http://www.stata.com/statalist/archive/2005-11/msg00123.html

Cheers,
Mark

Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3296
email: m.e.schaffer@hw.ac.uk
web: http://www.sml.hw.ac.uk/ecomes
 

> I realize that I can get around these problems doing the 
> regression manually, but I don't want to have to deal with 
> correcting the standard errors (I'm not sure how to do that 
> correctly).  
>  
> However, if I was to do that, I found the formula (2SLS 
> variance)/(SSTx*R^2x,z) in Wooldridge, but there isn't much 
> explanation.  Exactly what regression is SSTx coming from?  
> Is R^2x,z just R^2 from the first stage?  Is the denominator 
> a constant or is it changing with each xi?
>  
> Thanks very much, I appreciate any help.  -Kris
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 
> 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index