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

RE: st: two-stage probit least squares


From   "Sirois, Maureen" <Maureen.Sirois@puc.state.nh.us>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: two-stage probit least squares
Date   Wed, 13 Aug 2003 15:24:18 -0400

Could I apply ivprob to an ordered probit model.  Perhaps I could use
ivoprob.  

What I'm trying to do is estimate an order probit model that has a
series of independent variables.  I suspect that there is sample
selection in regard to one variable, which happens to be a dummy
variable.  With this Treatment Effects model, I was hoping to derive the
inverse mills ratio using the simple ordered probit (with the end. Dummy
variable).  Then I think I would use the inverse mills ratio to estimate
a new equation, so that it would be treated has an independent variable
along with the others.

I was thinking that I could manipulate the heck command in some way, but
the e-mail below suggests a possible alternative.  I would greatly
appreciate some suggestions.

Sincerely, 

Maureen L. Sirois, ABD
Utility Analyst
New Hampshire Public Utilities Commission
8 Old Suncook Rd.
Concord, NH 03301-7319
e-mail: maureen.sirois@puc.state.nh.us
(603)271-2431

-----Original Message-----
From: Mark Schaffer [mailto:M.E.Schaffer@hw.ac.uk] 
Sent: Wednesday, August 13, 2003 2:38 PM
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: two-stage probit least squares

Emiko,

-ivprob- might do what you want.  You can use it to estimate a single-
equation probit in which one or more RHS regressors is endogenous.  
You would need to investigate whether it matters if your RHS 
endogenous regressor is a 1/0 variable or not.

Hope this helps.

--Mark

Date sent:      	Tue, 12 Aug 2003 15:42:17 -0700
From:           	emiko takagi <takagi@usc.edu>
Subject:        	st: two-stage probit least squares
To:             	statalist@hsphsun2.harvard.edu
Send reply to:  	statalist@hsphsun2.harvard.edu

> Hi,
> 
> I would like to test a model with two binary dependent variables
> that are correlated with each other.  The ideal approach seems to
> be 2SLS; however, because of the binary natures of the endogeneous
> variables, I believe the 2SLS will produce inconsistent results.
> Is it possible to run two-stage probit least squares in STATA? 
> 
> Emiko Takagi
> 
> *
> *   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/

*
*   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