Statalist


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

Re: st: oheckman


From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: oheckman
Date   Fri, 11 Jan 2008 16:11:21 +0000 (GMT)

This looks to me that you are not using instrumental 
variables to identify your model, i.e. you need to 
find a variable that influences market participation
status but not sales/puchases. Than you need to 
exclude those variables from the indepvars list and
include it in the indepvars_sel list (in the 
-select()- option). 

This need for instrumental variables is in my humble 
opinion a major weakness of these heckman-type models 
because such variables almost never exist...

-- Maarten

--- "Ana R. Rios" <[email protected]> wrote:
> Thank you for your suggestions.  The dependent
> variable in my model is the volume of sales/purchases
> and the selection variable is the market participation
> status: 0=net buyer, 1=autarkic, 2=net seller.  As
> dependent variables in the model I am using household
> and farm characteristics.
> 
> I have been using the twostep estimation procedure and
> experimented with different explanatory variables.    
> 
> I got the oheckman command in the official help files,
> FAQs, Examples, SJs, and STBs.  A detailed description
> of the command is available in The Stata Journal 2007,
> 7(2):1-16. 
> 
> Once again, any advise/suggestions are greatly
> appreciated.
> 
> Thank you for your time.
> 
> Regards,
> 
> Ana Rios
> --- Maarten buis <[email protected]> wrote:
> 
> > --- "Ana R. Rios" <[email protected]> wrote:
> > > I am trying to use oheckman but I am getting the
> > > following message:
> > > "Warning: Estimate of rho1 = . is outside feasible
> > > interval [-1, 1]."
> > > I would appreciate any suggestions/insights on how
> > to
> > > overcome this problem.
> > 
> > It seems that -oheckman- has "converged" to an 
> > infeasible solution. The solution is to estimate a
> > better model, as you haven't told us anything about
> > your model I can't be very specific. One thing that
> > jumps to mind with any heckman-like model is to make
> > sure your model is properly identified, i.e. use 
> > instruments instead of relying on non-linearity.
> > Another thing you might want to look at is to use
> > the -twostep- option and see if that leads to any
> > better estimates.
> > 
> > -- Maarten
> > 
> > BTW. -oheckman- is not in official Stata, so tell
> > us where you got it.
> > 
> > -----------------------------------------
> > Maarten L. Buis
> > Department of Social Research Methodology
> > Vrije Universiteit Amsterdam
> > Boelelaan 1081
> > 1081 HV Amsterdam
> > The Netherlands
> > 
> > visiting address:
> > Buitenveldertselaan 3 (Metropolitan), room Z434
> > 
> > +31 20 5986715
> > 
> > http://home.fsw.vu.nl/m.buis/
> > -----------------------------------------
> > 
> 
> 
>      
>
____________________________________________________________________________________
> Never miss a thing.  Make Yahoo your home page. 
> http://www.yahoo.com/r/hs
> *
> *   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/
> 


-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      __________________________________________________________
Sent from Yahoo! Mail - a smarter inbox http://uk.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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index