> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Ada Ma
> Sent: 25 November 2003 12:20
> To: [email protected]
> Subject: st: any shortcut for oaxaca decomposition
>
>
> Hi,
>
> I am doing some oaxaca decompositions and I'm looking for
> some shortcuts,
> thus I ran the two following estimations:
>
> [1] separate estimations for male and female: wage = alpha +
> beta1*gamma +
> beta2*zeta
>
> [2] one estimation, but with interactive dummies (female = 1
> for women)
> wage = alpha + beta1*gamma + beta2*zeta + beta3*female +
> beta4*female*gamma + beta5*female*zeta
>
> Now my question is why is it that the estimated beta1 in [2]
> differ from
> that of beta1 in the male estimation in [1]? And why is it that the
> summation of beta1 and beta4 in estimation [2] would equal to
> beta1 for
> females in estimation [1]?
>
> I know I'm making different assumptions regarding the error terms in
> estimations [1] and [2], but what elses are driving the differences?
At first glance I don't know the answer to your question, but note that
users have written commands to do these sorts of decompositions (both
available via -ssc- command): -decomp- and -decompose-
Stephen
-------------------------------------------------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374. Fax: +44 1206 873151.
http://www.iser.essex.ac.uk
*
* 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/
