Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -heckman- and -ivreg- AT THE SAME TIME


From   Ketan Patel <ketan@mit.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -heckman- and -ivreg- AT THE SAME TIME
Date   Mon, 31 Oct 2005 19:43:47 -0500

Hi Tinna,

If I understand your problem correctly and you are willing to use the
Heckman Two-Step procedure (instead of ML), you could split the
Heckman into the individual steps, and manually compute the inverse
Mills ratio.

The first step is the selection model, from which you can compute the
inverse Mills, and include that in your IV regression.  Code follows:

probit WorkedFullTime XVector
predict Z, xb
gen InvMills = normden(Z) / norm(Z)

ivreg2 HoursWorked XVector InvMills

--Ketan Patel

On 10/31/05, Tinna <statalist@gmail.com> wrote:
> Dear statalisters,
>
> I need to control for selection in the model I am estimating (e.g.
> -heckman-), but I also suspect endogeneity (-ivreg2-). (see further in
> P.S. if needed)
>
> Is there a command that allows me to do both at the same time?
>
> Any suggestions or thoughts are appreciated.
>
> Tinna
>
> P.S. Basically I am estimating an hours worked equation, where I only
> have hours worked for those who's main activity is working (as opposed
> to being a student, disabled, retired, homemaker...). It is the
> coefficient of interest in this equation that is likely to be biased
> if not instrumented.
>
> *
> *   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index