I was aware of -svymean-, as I presume
was the original questioner. Whether
the questioner is better off cycling
around -svymean- or doing things some
other way I cannot say. But, to extend
what I said, I am not aware of any -egen- function
geared to -svy- problems, which was the original
question.
David's function _gwtmean does not
come with a help file and the
description in the package file is very brief.
However, looking at the code I see no
indication that it will treat pweights as such.
-svy- is unexplored territory to me, so it
really needs an expert to comment further.
Nick
[email protected]
David Kantor
> Nick cox replied, in response to questions from Anant Thaker:
>
> At 06:13 AM 3/7/2006, you wrote:
> >-egen- always follows a syntax
> >
> >egen newvar = fcn() ...
> >
> >and I am not aware of a -egen- function -svymean()-.
> >
> >[...]
>
> I would add, at the risk of stating the obvious, that there is a
> -svymean- command in standard Stata. It has nothing to do with -egen-.
>
> Also, if you want a weighted mean in an -egen- context, try the
> _gwtmean package from SSC:
> ssc desc _gwtmean
> ssc install _gwtmean
>
> But, I can say whether any of this is useful for the problem at hand.
*
* 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/
