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

st: predict using heckman


From   Alfredo Ariza Alfaro <[email protected]>
To   statalist <[email protected]>
Subject   st: predict using heckman
Date   Mon, 18 Jul 2005 12:52:05 +0200

I am using heckman to estimate a wage equation. I would like to impute wages to non participants. In order to have predicted wages for non participants I can not use some independent variables like tenure, experience,etc. cause they are not available for non participants. So, I would like to use the variance of the prediction to improve my imputations (using two moments of the distribution instead of only one).

I am not sure of what Stata calculate using "predict stdf". Is this the variance of the prediction, taking into account the hazard (mills ratio)?

What is the difference between predict stdf and stdp in Hecman?


Thank you. Regards.


--
Alfredo Ariza Alfaro
Departamento Econom´┐Ża y Empresa
Universidad Pablo de Olavide
Carretera Utrera, km.1 Edificio 3, planta 4, despacho 2
41013 SEVILLA, Spain
telf. + 34 954 34 9187
Fax. + 34 954 34 9339
http://webdee.upo.es/aarialf

e-mail:[email protected]

"I disapprove of what you say, but I will
defend to the death your right to say it." (The Friends of Voltaire, 1906)

*
* 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