Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: IV list in ivreg and ivreg2


From   "Mark Schaffer" <[email protected]>
To   [email protected]
Subject   Re: st: IV list in ivreg and ivreg2
Date   Mon, 19 Apr 2004 15:49:19 +0100

Eddy,

Date sent:      	Mon, 19 Apr 2004 04:39:53 -0700 (PDT)
From:           	Eddy <[email protected]>
Subject:        	st: IV list in ivreg and ivreg2
To:             	[email protected]
Send reply to:  	[email protected]

> Dear listers,
> 
> When using ivreg or ivreg2 to do a 2SLS estimation, all the RHS
> variables except those explicitly specified as endogenous are assumed
> to be exogenous and valid IV. Call those the "included exogenous
> variables". However, I happen to have a case in which not all the
> "included exogenous variables" are valid IV, and I am asking whether
> users can have better control over the list of IV to be used in the
> 2SLS estimation.

I'm not sure this makes sense.  A "valid" IV is one that satisfies 
the orthogonality conditions; this is synonymous with "exogenous".  
If one of your regressors isn't a valid IV, then it isn't exogenous 
and you need to treat it as endogenous.  This is the way that IV 
works (or, in modern presentations, GMM with IV as a special case).

In your example, ln(P) might or might not be be orthogonal to the 
disturbance term.  If it is, it's a valid IV and you can treat it as 
exogenous; if it isn't, it's not a valid IV and you should treat it 
as endogenous.  It sounds like you lean towards the latter, which 
looks like a reasonable way to proceed (so long as you have enough 
other valid excluded instruments to identify the equation, and they 
are "relevant" as well as "valid").

Hope this helps.

--Mark

> 
> The model I am dealing with is from the precautionary saving
> literature, in which a commonly used regression model is something
> like:
> 
>   ln(W/P) = a0 + a1*ln(P) + a2*y + B*X,
> 
> where W is wealth, P is permanent income, y is the endogenous
> variable, and X are all other exogenous variables. Note that ln(P) is
> on the LHS as well as on the RHS; the literature has it on the RHS to
> "control for heterogenous preference".
> 
> The task is to control for the endogeneity of y and leave ln(P)
> alone, as most of the studies in this literature claimed to have
> done. With ivreg or ivreg2, all the RHS variables except y are
> automatically included in the IV list. However, ln(P) is clearly not
> a valid IV. Therefore, I would like to have a IV list that does not
> include ln(P). This problem can be solved if users can have the
> freedom in specifying the IV list, but apparently ivreg and iverg2
> are not written based on this idea.
> 
> I have been thinking of specifying both y and ln(P) as the endogenous
> variables in order to treat the program, but I am afraid the result
> is NOT what I (and the literature) set out for: control the
> endogeneity of y and leave ln(P) alone.
> 
> Any thought?
> 
> 
> Eddy
> 
> 
> 	
> 		
> __________________________________
> Do you Yahoo!?
> Yahoo! Photos: High-quality 4x6 digital prints for 25�
> http://photos.yahoo.com/ph/print_splash
> *
> *   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/


Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS  UK
44-131-451-3494 direct
44-131-451-3008 fax
44-131-451-3485 CERT administrator
http://www.som.hw.ac.uk/cert

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index