st: RE: Oaxaca decomposition

["Rubil Ivica" <irubil@eizg.hr>]

Vicky,

concerning quaestion 1, what you need is the option "eform", which will
give you exponentiated results. As you know, exp(ln(x))=x.

Regards,
ivica

// ir //


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Vaidyanathan
Ganapathy
Sent: Tuesday, March 04, 2014 6:33 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: Oaxaca decomposition

I am using the -Oaxaca command in STATA to perform a decomposition of
ln(healthcare costs) on various predictors to study the differentials
between two groups. I have two related questions:

1) When I use ln(healthcare costs) as the outcome, the differentials
obtained are differences in ln(healthcare costs). I have read the Oaxaca
help file, but couldn't see if there is a way that the explained and
unexplained differences can be retransformed and interpreted in real
dollars (i.e. retransformed from ln(costs) to costs)? Has anyone got any
suggestion how to do this?

2) The Oaxaca estimation command doesn't seem to work with xtreg
(Error: "xtreg is not available with suest"); Does this mean that fixed
effects models cannot be run using this command? Any thoughts?

Thanks,

Vicky
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/