Re: st:oaxaca decomposition after fixed effect analysis

[Dimitris Pavlopoulos <Dimitris.Pavlopoulos@soc.kuleuven.be>]

Dear Mandy,

before checking whether the syntax is correct you should consider how   
to apply an oaxaca after a fixed effects regression. If you have time  
constant predictors there is a lot of bias involved. Please see the  
following reference as an example:

ftp://repec.iza.org/RePEc/Discussionpaper/dp1886.pdf

best regards,
Dimitris



Quoting Man Jia <jia.m@neu.edu>:


> Hi all,
>
> I'm going to do oaxaca decomposition with the fixed effect estimators
> in a panel data set. I haven't done this before, so I'll appreciate if
> you let me know any problem in my following commands. It'll be great if
> there's easier way to deal with this.
> Thanks for your help!
>  -----------------------------------------------------------------
>   ***model y[i,t] = B*x[i,t] + u[i] +t + e[i,t]
> . xtreg y x,few
> . predict y_demean ,xb
>   ***x_demean =y[i,t]-mean of y[i,t]
>   ***x_demean is the created variable =x[i,t]-mean of x[i,t]
> . oaxaca y_demean  x_demean
> -----------------------------------------------------------------
> Thank you very much! I really appreciate it.
> Regards,
>
> Mandy
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/


********************************************************************
dr. Dimitris Pavlopoulos

International Master in Social Policy Analysis (IMPALLA)
University of Leuven
OE CeSO, room 02.27
Parkstraat 45 - bus 3601
3000 Leuven
Belgium

tel: +32 (0)16 323151
email: dimitris.pavlopoulos@soc.kuleuven.be
********************************************************************

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm


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