Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: oaxaca blinder decomposition after cox


From   Nihan Blanchy <Ozge-Nihan.Koseleci@malix.univ-paris1.fr>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: oaxaca blinder decomposition after cox
Date   Fri, 20 Jun 2008 12:20:15 +0200

Thanks a lot!
--
Mme. Nihan BLANCHY
Doctorante
00 33 (0)6 09 18 32 98
Centre d'Economie de la Sorbonne
UniversitÚ Paris 1 Pantheon Sorbonne, CNRS
Boulevard de l'H˘pital 106-112
75647 Paris Cedex 13



Selon Austin Nichols <austinnichols@gmail.com>:

> Nihan Blanchy <Ozge-Nihan.Koseleci@malix.univ-paris1.fr>:
> See also
> http://ftp.iza.org/dp877.pdf
> and other related papers by Yun at http://www.iza.org.
>
> On Thu, Jun 19, 2008 at 5:52 AM, Maarten buis <maartenbuis@yahoo.co.uk>
> wrote:
> > --- Nihan Blanchy <Ozge-Nihan.Koseleci@malix.univ-paris1.fr> wrote:
> >> I try to implement the Oaxaca-Blinder decomposition after semi
> >> parametric cox regression to measure the extent to which the
> >> differences in predicted hazard rates out of unemployment between
> >> two different groups can be explained by differences in their
> >> average observable characteristics.
> >
> > These decomposition techniques rely heavily on linearity, as this will
> > cause many complications to cancel out. As a consequence they don't
> > play well with non-linear models like -stcox-, -logit-, etc. How to
> > make them work in these non-linear models is still an area of active
> > research.
> >
> > One approach that you might be able to extend to xtcox is by Robert
> > Fairlie (1999, 2003, 2005), implemented by Ben Jann in Stata as the
> > -fairlie- package, which can be downloaded from -ssc-. Notice that this
> > package is not directly applicable to -stcox-, but my hunch is that the
> > principle can be extended to -stcox-.
> >
> > An alternative approach that might also work is by Erikson and
> > collegues (2005), which is implemented by me as the -ldecomp- package,
> > also downloadable form -ssc- and discussed in (Buis 2008). Again, I am
> > talking about the principle, the package is not directly applicable to
> > -stcox-.
> >
> > Hope this helps,
> > Maarten
> >
> >    Buis, M.L. (2008). Direct and indirect effects in a logit model.
> > http://home.fsw.vu.nl/m.buis/wp/ldecomp.html
> >
> >    Erikson, R, J.H. Goldthorpe, M. Jackson, M. Yaish, D.R. Cox (2005).
> >  On class differentials in educational attainment.  Proceedings of the
> > National Academy of Science, 102(27): 9730-9732.
> >
> >    Fairlie, Robert W. (1999). The Absence of the African-American
> > Owned Business: An Analysis of the Dynamics of Self-Employment. Journal
> > of Labor Economics 17(1): 80-108.
> >
> >    Fairlie, Robert W. (2003). An Extension of the Blinder-Oaxaca
> > Decomposition Technique to Logit and Probit Models. Economic Growth
> > Center, Yale University Discussion Paper No. 873.
> >
> >    Fairlie, Robert W. (2005). An extension of the Blinder-Oaxaca
> > decomposition technique to logit and probit models. Journal of Economic
> > and Social Measurement 30: 305-316.
> >
> *
> *   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/
>
> --
> Ce message a ete verifie par MailScanner
> pour des virus ou des polluriels et rien de
> suspect n'a ete trouve.
>


----------------------------------------------------------------
This message was sent using IMP, the Internet Messaging Program.

-- 
Ce message a ete verifie par MailScanner
pour des virus ou des polluriels et rien de
suspect n'a ete trouve.

*
*   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