From: "Stephen P. Jenkins" <[email protected]>
Reply-To: [email protected]
To: [email protected]
Subject: Re: st: boostrapping decomposed measures of inequality
Date: Wed, 14 May 2003 10:47:32 +0100 (GMT Daylight Time)
On Tue, 13 May 2003 23:01:57 +0000 Polly Smiths
<[email protected]> wrote:
> Dear all:
> Might anyone have any ideas on how to bootstrap inequality measures once
> they are decomposed into between and within-group components? (they are
> calculated using ineqdeco).
The current version of -ineqdeco- saves as global macros the total
inequality measures but not the subgroup inequalities or the Within or
Between group inequality, for each of the various GE indices. If it did
save these stats, then it would be straightforward to bootstrap all the
stats, jointly.
When I wrote -ineqdeco-, I didn't have it save those subgroup-related
stats because the number of subgroups is not known in advance, and
hence complications in labelling all the stats. I now know that there
are potential ways around this, and I'll consider incorporating them in
a revised version of the program (when I get the time to do it!).
Meanwhile, I suggest that you produce a problem-specific version of the
program -- rename -ineqdeco- to something else, and then do some
"hard-wiring" -- add some command lines that save the stats you want
for your data. And then bootstrap
Stephen
----------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research (ISER)
University of Essex, Colchester, CO4 3SQ, UK
Tel: +44 (0)1206 873374. Fax: +44 (0)1206 873151.
http://www.iser.essex.ac.uk
*
* 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/
_________________________________________________________________
