st: Generate quartile adjusted by subpopulation

[Xavi Barber <xbarber@altern.org>]

Dear statalister:

        I have 4 subpopulation (group A (n=200), B(n=200), C(n=200), D(n=400))

        I need to create a new categorical variable, this variables is the 
4Q-tile of variable varXXX but the distribution of the quartile  is 
according to subpopulation D.

        I use the xtile & the xtile2 command, but I not sure than the new 
4Q variable is ok.

FOR EXAMPLE:

        xtile2 var4Q=varXXX ,  nq(4) by(grupD)

but grupD have 600 missing and the new variable var4Q have 400 observations 
and not 1000.

Can You help me? 
*
*   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/