st: RE: permutations and sorting percentiles

["Martin Weiss" <martin.weiss1@gmx.de>]

<>

***********
ssc d selectvars
***********


HTH
Martin

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Gautam,
Sanghmitra
Sent: Mittwoch, 25. August 2010 19:42
To: statalist@hsphsun2.harvard.edu
Subject: st: permutations and sorting percentiles 

Hi 

I have two questions and the second follows in continuation from the first

1. I want to create all possible permutations and combinations of people in
a village and I was wondering if STATA allows for that ? I have data by each
village - n people (each with own st. dev of income) and divided into z
number of groups and each group is of size k. 
So I want to form all possible groupings i.e. (n choose k)/z

2. I have previously calculated rank ordering metric Ktau (for all villages)
on the original observed groupings and from procedure (1) above will have
the Ktau metric for all combinations of groupings. How would one calculate a
sorting percentile range for the observed grouping: i.e. an [a,b] where a%
of groups have a strictly lower K-tau and b% a strictly higher K-tau than
the observed grouping.

Thank you 
Sanghmitra
*
*   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/

*
*   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/