Dear Shige,
I guess you may want to use some "density estimation" procedures. Stata
7.0 has "kdensity" procedure, which estimate univariate density. I am
not sure whether there exist multivariate density estimation procedure.
Skyang
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Shige Song
Sent: Sunday, March 02, 2003 4:57 PM
To: [email protected]
Subject: st: Questions about quantile
Dear All,
I want to do a regression-type analysis to determine the location
(quantile) of a specific value in the distribution. For example, "what
quantile will $4000 will be in the American monthly income distribution
in
1999?" and "what is the effect of educational attainment on this?"
Quantile
regression is very convenient for question like "what is the value of
the
80th quantile of ...", my questions is kind of like its opposite.
Thanks!
Best,
Shige Song
Department of Sociology, UCLA
*
* 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/
BEGIN:VCARD
VERSION:2.1
N:Yang;Shinkyu;;Professor
FN:Shinkyu Yang
ORG:New York University
TITLE:Professor
TEL;WORK;VOICE:(212) 998-0818
TEL;HOME;VOICE:(212) 777-5199
TEL;CELL;VOICE:(917) 407-4712
TEL;WORK;FAX:(212) 995-4228
TEL;HOME;FAX:(212) 504-7917
ADR;WORK;ENCODING=QUOTED-PRINTABLE:;;44 West 4th St.=0D=0ASuite 8-94;New York;NY;10012;United States of America
LABEL;WORK;ENCODING=QUOTED-PRINTABLE:44 West 4th St.=0D=0ASuite 8-94=0D=0ANew York, NY 10012=0D=0AUnited States o=
f America
EMAIL;PREF;INTERNET:[email protected]
REV:20030212T233941Z
END:VCARD
