Dear Natalia,
Yes, -decomp- does use the mean of each of the rhs variables from
the regressions. Only the constant is omitted from this calculation
and enters the final results by having its coefficient multiplied by
1. All of the other rhs variables have their coefficients multiplied
by the relevant means.
The formula is implemented in -decomp- using matrices and employs
the exact formula used by Blinder. Earlier versions of -decomp- used
rather cryptic matrix and macro names but in the latest version
(1.5) I have renamed all matrices and macro into more fullsome
terms, which should make it much easier for people who want to
inspect the code. If you open himod.ado and decomp.ado in a text
editor you can see for yourself how the means and coefficients are
manipulated.
--
Kind regards,
Ian
=====================
Ian Watson
Senior Researcher
acirrt
University of Sydney
NSW 2006
Australia
======================
Friday, October 15, 2004, 1:32:41 AM, you wrote:
NNFB> Hi
NNFB> IŽm using de comand "decomp" to calculate
NNFB> Blinder-Oaxaca decomposition for the
NNFB> first time, and I just want to be sure that this command calculates de
NNFB> decomposition of the mean. In the "decomp" help do not have any comments about
NNFB> in each point of the sample de Blinder Oaxaca decomposition is calculate.
NNFB> Thanks, Natalia B.
NNFB> ________________________________
NNFB> Pós Graduação IPE/USP
NNFB> *
NNFB> * For searches and help try:
NNFB> * http://www.stata.com/support/faqs/res/findit.html
NNFB> * http://www.stata.com/support/statalist/faq
NNFB> * 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/
