Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: bootstrap test for ineqdeco comparison


From   Gianluca Cafiso <gcafiso@unict.it>
To   statalist@hsphsun2.harvard.edu
Subject   st: bootstrap test for ineqdeco comparison
Date   Fri, 08 May 2009 13:50:56 +0200

Dear All,

I need to test if the concentration index (CI) for a sample of
geo-units has changed over time trough a bootstrap procedure. I have the employment value for the
same geo-units in two different points in time, I want to test if the
CI in t1 is equal to the CI in t2 (as done in Brulhart+Traeger 2005).

To compute the index, I have used the "ineqdeco" routine separately
on the Employment variable for t1 and then on the one for t2.

However, I do not know how to implement the bootstrap test. Because, I cannot write the command:

bootstrap diff=(r(ge1)"t1"-r(ge1)"t2"), reps(#): ineqdeco emp, by(id)

since ineqdeco computes only one CI, the one for the variable
listed and I cannot indicate the two different periods.

I guess that this is similar to the case when one wants to test if
the sample mean changes over time through a bootstrap test. Indeed,
sum "var", generates only one value even if one would like to differentiate between two clusters of "var".

Can anyone provide me with suggestions?

Thanks, Gianluca Cafiso.




----------------------------------------------------------------
Università di Catania - C.E.A.
Servizio di Posta Elettronica
http://www.cea.unict.it


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index