Re: st: deriving a bootstrap estimate of a difference between two weighted regressions

[Stas Kolenikov <skolenik@gmail.com>]

Then your standard errors won't be right, and you'd have to do
something about it. Probably bootstrap :))

On Mon, Aug 2, 2010 at 9:45 AM, Steve Samuels <sjsamuels@gmail.com> wrote:
> I didn't notice that the weights could be negative.  Thanks for
> catching that, Stas! Observations with negative pweights and aweights
> will be excluded.  You'll have to compute the weighted responses by
> hand:  weighted response = old response  times weight, and use -reg-
> or -egen- to get the difference in the means of the  weighted
> responses.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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/