Statalist


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

RE: st: -heckman- and the identifying variable(s)


From   Louis Boakye-Yiadom <lby_kw@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   RE: st: -heckman- and the identifying variable(s)
Date   Tue, 16 Oct 2007 09:12:45 +0100 (BST)

Many thanks for this. Is this suggestion applicable to
only the ml version of -heckman-? Thanks.

Louis


--- "Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk> wrote:

> Louis,
> 
> > -----Original Message-----
> > From: owner-statalist@hsphsun2.harvard.edu 
> > [mailto:owner-statalist@hsphsun2.harvard.edu] On
> Behalf Of 
> > Louis Boakye-Yiadom
> > Sent: 15 October 2007 14:18
> > To: statalist@hsphsun2.harvard.edu
> > Subject: Re: st: -heckman- and the identifying
> variable(s)
> > 
> > Thanks. I was hoping there is an equivalent of the
> Sargan test.
> 
> If you're willing to be specific about which of the
> overidentifying
> restrictions you have doubts about, you can estimate
> using -heckman- and
> ML and do a LR test.  That is, do one estimation
> with the full set of
> identifying variables, do a second estimation
> omitting the ones you have
> doubts about, and do your LR test.  The
> interpretation is the same as
> that in the IV context - under the null, the test
> stat should be
> distributed as chi-sq with dof=#omitted identifying
> variables.
> 
> HTH.
> 
> 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
> 
> > Louis
> > 
> > Quoting Maarten buis <maartenbuis@yahoo.co.uk>:
> > 
> > > --- Louis Boakye-Yiadom
> <L.Boakye-Yiadom@bath.ac.uk> wrote:
> > >> When using the -heckman- command, is there a
> way of checking the 
> > >> validity of the identifying variable(s)?
> > >
> > > No, that is the big problem with every type of
> "causal" 
> > model, in the 
> > > end they rely on assumptions you just have to
> believe. Descriptive 
> > > models are in that sense much more scientific.
> > >
> > > -- Maarten


      ___________________________________________________________ 
Want ideas for reducing your carbon footprint? Visit Yahoo! For Good  http://uk.promotions.yahoo.com/forgood/environment.html
*
*   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