Re: st: Hurlde models

["Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>]

Dear Jon

  I wonder if this article from the Stata Journal about hurdle models is helpful.

http://www.stata-journal.com/sjpdf.html?articlenum=st0040

  I hope this might help,

Michael N. Mitchell
Data Management Using Stata      - http://www.stata.com/bookstore/dmus.html
A Visual Guide to Stata Graphics - http://www.stata.com/bookstore/vgsg.html
Stata tidbit of the week         - http://www.MichaelNormanMitchell.com



On 2010-06-02 11.47 PM, John Ataguba wrote:
> Dear members
>
> This may sound simple but I have been trying to understand using the Hurdle models.  This is a two-part model but I wonder if the two parts are estimated in some sort of independent ways.  By this I mean running the probit (or any other binary choice model) in the first instance, and for those that cross the hurdle, run a truncated-at-zero count model for instance.
>
> Basically my question is then: Do we need anything estimated from the first part introduced into the second part to correct for any thing?  This is because the Heckman model (though this is two-step and not two-part) includes something like the inverse of Mill's ratio.  I was just wondering if you would need something similar to this in the second part of a hurdle model.
>
> Any useful suggestion on this will be appreciated.
>
> Regards
>
>
> Jon
>
>
>
>
>
>
> *
> *   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/
*
*   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/