> I have long benefited from reading the insightful
> contributions from so many of you. Meanwhile, I have a
> question regarding how to use Stata to construct a measure of
> economic inequality. I have regional-level average per capita
> GDP data for a country for about 20 years and I want to see
> how the regions differ from each other in level of economic
> wealth. A natural step forward seems to be calculating the
> Gini coefficients using regional level data. Somehow,
> however, I noticed that using the command -rspread- in Stata
> gives me different results for Gini from using the command
> -inequal-. There might be other similar commands that give
> still different output. I am just wondering which command I
> should use. Thanks so much in advance!
There are many commands available for calculating the Gini
and other inequality measures. (Try -findit inequality-.)
They include -inequal7- (an updated and extended version of -inequal-),
-ineqdeco- (which also allows decompositions by population subgroups),
and -glcurve- for Lorenz and related curves. Note that -inequal7- and
-ineqdeco- give the same results for corresponding indices. Both assume
that
all incomes are greater than zero (zero, negative and missing values are
not
used). If you want the Gini indices including zero values, use
-ineqdec0-.
All the programs mentioned can be obtained using the -ssc install-
command
Check the treatment of weights too in the different programs.
Stephen
-------------------------------------------------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374. Fax: +44 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/
