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

st: Re: HecKman two step procedure and prediction


From   "R.E. De Hoyos" <redeho@hotmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: HecKman two step procedure and prediction
Date   Thu, 23 Jun 2005 10:16:30 +0300

Alfredo,

The option -stdp- after -predict- in Heckman's estimation, produces the standard error of the fitted value. Where the fitted value derives from the "population" un biased parameters estimates, i.e. taking into account selectivity [y^hat = {xb^hat | Pr(y = observed | z)}].

I hope I got your question right,

Rafa
________________________
R.E. De Hoyos
Faculty of Economics
University of Cambridge
CB3 9DE, UK
www.econ.cam.ac.uk/phd/red29/

----- Original Message ----- From: "Alfredo Ariza Alfaro" <aarialf@upo.es>
To: <statalist@hsphsun2.harvard.edu>
Sent: Wednesday, June 22, 2005 7:47 PM
Subject: st: HecKman two step procedure and prediction



Hi everyone!
                     I want to predict  wages for women who do not work,
so I am using the Heckman two step procedure to calculate wages for
participants accounting for selection. To predict wages for non
participants accurately I want to use the standard error of the
prediction instead of using just the mean. Using "predict  var , stdp"
predicts the standard error of the prediction taking into account the
Mills ratio? Or is just calculating the standard error of the linear
regression without taking into account the selection?

Thank you very much.

Regards.

*
*   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