Statalist


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

RE: Repost: instrumental variables regression with random effects GLS using cross-section data and endogenous binary independent variable


From   "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: Repost: instrumental variables regression with random effects GLS using cross-section data and endogenous binary independent variable
Date   Mon, 8 Oct 2007 16:42:30 +0100

Renuka,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Renuka Metcalfe
> Sent: Monday, October 08, 2007 9:50 AM
> To: nicola.baldini2@unibo.it; statalist@hsphsun2.harvard.edu
> Cc: rm18203@yahoo.co.uk
> Subject: Re: Repost: instrumental variables regression with 
> random effects GLS using cross-section data and endogenous 
> binary independent variable
> 
> What I mean is I estimated initially a random effects GLS 
> model; now I want to correct for the endogenity between the 
> dependent and one of the independent variable which is a 
> binary variable as stated in my email below.

Why not use -xtivreg-?  It does IV random effects in two flavours (G2SLS
and EC2SLS), both of which are consistent whether or not the endogenous
regressor is binary or continuous.

HTH,
Mark

> --- nicola.baldini2@unibo.it wrote:
> 
> > I don't know what "ran random effects GLS" means, since you declare 
> > having a cross-section. -ivreg- (and related commands, such as 
> > -ivreg2-, -xtivreg-,
> > etc.) can be used with a dummy endogenous variable, too.
> > 
> > Nicola
> > 
> > At 02.33 05/10/2007 -0400, Renuka Metcalfe wrote:
> > >Dear Statalisters
> > >
> > >I have a cross-section data and my dependent
> > variable
> > >is continuous and I have one independent variable which is 
> endogenous 
> > >and is binary. I have an instrument for the endogenous binary 
> > >independent variable. I ran random effects GLS as follows
> > >
> > >Y x1 x2 x3 x4
> > >
> > >Since x4 is endogenous with Y, I now want to use an 
> instrument Z. Y 
> > >is a continuous variable x4 is an endogenous binary variable. The 
> > >data are also
> > grouped
> > >across workplaces.
> > >
> > >Looking at the archives it was suggested that a
> > probit
> > >be used for the first stage estimation of the independent 
> endogenous 
> > >binary variable. But the dependent variable there was censored.
> > >
> > >If you need further information please let me know.
> > >
> > >Thanks in advance
> > >
> > >Best wishes
> > 
> > 
> 
> 
> 
>       ____________________________________________________
> One email account is enough. Simplify your life by switching 
> other accounts into Yahoo! Mail.
> http://uk.docs.yahoo.com/mail/trueswitch_overview
> *
> *   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