Statalist The Stata Listserver


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

Re: st: -heckman-


From   Nishant Dass <nishant_dass@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -heckman-
Date   Mon, 16 Oct 2006 12:48:46 -0700 (PDT)

Robert,

Thanks for the clarification.

I have 4 variables in the selection equation that are
unique and 5 other variables that overlap with those from
the outcome equation.  So I understand my model should be
ok.

Thanks,

Nishant 

--- Robert Duval <rduval@gmail.com> wrote:

> Actually in this simple model X can equal W.
> This is because the Inverse Mills' Ratio is a nonlinear
> function of W
> so this can avoid perfect collinearity if W has a long
> enough support.
> 
> In practice though, it is better to have at least one
> variable
> excluded from X in order to achieve better
> identification.
> 
> robert
> 
> On 10/16/06, Nishant Dass <nishant_dass@yahoo.com> wrote:
> > Philip,
> > Thank you for your succinct answer as well as the
> refernce;
> > I will check the book.
> > Regards,
> > Nishant
> >
> > --- Philip Fridborn
> <Philip.Fridborn.4605@student.uu.se>
> > wrote:
> >
> > > Hi,
> > > According to Wooldridge (2002) Econometric analysis
> of
> > > x-section and panel data
> > > you must have at least one variable in the selection
> > > model that is not included
> > > in the y-equation. This variable(-s) is supposed to
> > > affect z but not y.
> > > So, X and W do not have to be completely distinct.
> > >
> > > Philip Fridborn
> > >
> > > Citerar Nishant Dass <nishant_dass@yahoo.com>:
> > >
> > > > Dear list-members,
> > > >
> > > > If I have the following Heckman selection model:
> > > >
> > > > y = a + b.X + e   (2nd stage)
> > > > z = c + d.W + u   (selection equation)
> > > >
> > > > Would you know whether X and W have to be
> completely
> > > > distinct?
> > > >
> > > > I thought they ought to be distinct but I have seen
> > > some
> > > > papers that use variables that are common to both X
> and
> > > W.
> > > >
> > > >
> > > > Does anyone have a good answer or know of a
> definitive
> > > > source on this?
> > > >
> > > > Thanks for your suggestions.
> > > >
> > > > Nishant
> > > >
> > > > __________________________________________________
> > > > Do You Yahoo!?
> > > > Tired of spam?  Yahoo! Mail has the best spam
> > > protection around
> > > > http://mail.yahoo.com
> > > > *
> > > > *   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/
> > >
> >
> >
> > __________________________________________________
> > Do You Yahoo!?
> > Tired of spam?  Yahoo! Mail has the best spam
> protection around
> > http://mail.yahoo.com
> > *
> > *   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/
> 


__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 
*
*   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