Statalist


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

st: Re:ordered Heckman help


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   stata list <statalist@hsphsun2.harvard.edu>
Subject   st: Re:ordered Heckman help
Date   Thu, 17 Jul 2008 07:07:28 +0100 (BST)

--- Sami Haile wrote:
> Thanks for the Reply. What I am intedning to do is to see what
> affects market participation and volume of sells/purchases. My
> dependent variable for the selection equation( ordered probit) is
> Market participation whic is 0 for net buyer, 1 Autarkic and 2 For
> net seller.
> independent variables include household heade gender, household heade
> age, household heade age squared, household size, dependancy ratio,
> household assets, land, herd size, animal birth, animal theft and
> income (instrumented with herd size, land area, animal birth, animal
> theft, household size and education)
>  
> My dependent variable of the second step regression is net market
> (which is quantity sold or bought)
> and independent variables include household heade gender, household
> heade age, household heade age squared, household size, dependancy
> ratio, household assets, land, herd size, animal birth, animal theft
> and income (instrumented with herd size, land area, animal birth,
> animal theft, household size and education)
>  I tried to do it this way: 
> oheckman net market =household heade gender, household heade age,
> household heade age squared, household size, dependancy ratio,
> household assets, land, herd size, animal birth, animal theft and
> income select (Market surplus=household heade gender, household heade
> age, household heade age squared, household size, dependancy ratio,
> household assets, land, herd size, animal birth, animal theft and
> income)
>  
> I got I got a Warning: Two-step initial estimate of rho0 = 1.1182849
> truncated to +/-.85.
> Warning: Two-step initial estimate of rho1 = . truncated to +/-.85.
> It couldnt run at all..... Sometimes it also says logliklihood isnt
> concave....This is when I tried it with the default FMLE, when I
> tried it with two step some times it gives me solution but with the
> warning that rho is out side [-1,1]... Can you tell me what could be
> the reason? The Other thing is After the ordered probit or selection
> equation I expected two regressions only, one for net sellers and one
> for net buyers assumimng that the Autarkic will show up in both
> regressions.....But I got three regressions for each of them....Is
> that the way it should be? If now what is the command to get two
> regressions afre ordered probit selection model.

I don't know, that's one of the reasons why you should reply to the
Statalist and not to individual member, see the Statalist FAQ point 5.

-- Maarten

-----------------------------------------
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/
-----------------------------------------


      __________________________________________________________
Not happy with your email address?.
Get the one you really want - millions of new email addresses available now at Yahoo! http://uk.docs.yahoo.com/ymail/new.html
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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