Re: st: Quantile Regression with FE

[Gordon Hughes <G.A.Hughes@ed.ac.uk>]

You can apply the standard within transformation to your data 
manually by deducting the mean (or median) values of the dependent 
and independent variables for each panel unit from all 
observations.  This will eliminate the panel fixed effects.  You can 
recover the fixed effects in the usual way from the average or median 
values of the residuals for each panel unit.

However, you should think quite carefully about what it is that you 
are estimating.  There is a substantial literature among those 
interested in quantile regression about what the precise meaning of 
the conditional quantiles generated by these models - for example 
read the textbooks by Cameron & Trivedi or Wooldridge.  By removing 
the fixed effects you would be estimating conditional median 
deviations from the mean/median values of the observed 
variables.  This may or may not be what you are trying to obtain.

Gordon Hughes
g.a.hughes@ed.ac.uk
 

*
*   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/