I believe (though I can no longer locate the paper) Buchinsky (1995)
recommended bootstrapping to obtain estimates of the standard errors, as it
performed well in relatively small samples.
Buchinsky, M. (1995), "Estimating the Asymptotic Covariance Matrix for
Quantile Regression Models: A Monte Carlo Study," Journal of Econometrics,
68, 303-38.
Hope this helps,
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Nick Cox
> Sent: Monday, February 07, 2005 3:48 PM
> To: [email protected]
> Subject: st: RE: Re: RE: Fw: Sample size and QREG
>
> That's my only real idea here.
>
> I did think of getting a larger
> dataset (real or concocted) and
> reducing it by random deletion,
> but there's always a question
> of how relevant that would be to
> your real problem.
>
> Nick
> [email protected]
>
*
* 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/
