Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Clustering with bootstrap using quantile regression


From   "Arantxa Roca-Feltrer" <Arantxa.Roca-Feltrer@lshtm.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Clustering with bootstrap using quantile regression
Date   Mon, 20 Nov 2006 14:06:47 +0000

Dear all,
 
I am modelling the median age of children using quantile regression but
data comes from different countries and therefore I want to cluster by
country.
The only way (that I know) is to use bootstrap in order to be able to
cluster. However since apparently the number of clusters (countries) is
small (n=9) I am getting very weird values for the coefficients, either
very small or very large.
 
Does anyone know a better way of obtaining appropriate CIs for quantile
regression if I need to cluster (account for the fact that children from
the same country are non-independent i.e. might share same population
characteristics)???
 
Thanks
 
Arantxa 
 
 
*
*   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/



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