Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | David M Kaplan <dkaplan@ucsd.edu> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | st: qreg standard errors underlying formula |
| Date | Wed, 1 Dec 2010 15:31:16 -0800 |
Hi all,
I am wondering, does anybody know how Stata 11 calculates standard
errors for qreg?
The best information I currently have is footnote 6 from Koenker and
Hallock (2000), on page 16 of
http://www.econ.uiuc.edu/~roger/research/intro/rq.pdf ; which suggests
that Stata uses an approach based on Siddiqui (1960) with m=n^{1/2}.
I ran some simulations that approximately support this (they support
the rate of m, at least), but any information more specific, or
different, than that would be greatly appreciated!
Dave
*
* 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/