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

st: RE: decomposition of Theil inequality measures

From   "Giovanni Vecchi" <[email protected]>
To   <[email protected]>
Subject   st: RE: decomposition of Theil inequality measures
Date   Tue, 11 Sep 2007 22:29:28 +0200

Hi Borge,

try 'findit ineqdeco'

After installing the ado file, read the help file. You will see that
the Theil index corresponds to "GE(1)" in ineqdeco's parlance.

All the ingredients to carry out both the "static" decomposition of
the index (Shorrocks 1980, Econometrica) and the "dynamic"
decomposition (Mookherjee and Shorrocks 1982, Economic Journal) are
easily accessible among the saved results of ineqdeco. 

You will probably want to use the option by() in order to get the
pieces of information you need.

Note that other ado files are available, and you may wish to check
them. In my experience, however, ineqdeco is an excellent tool.

Best regards,


Giovanni VECCHI
Associate Professor
Department of Economics
University of Rome Tor Vergata

voice   + 39 06 7259 5730
fax     + 39 06 2020 500
email   [email protected]

> -----Original Message-----
> From: [email protected] 
> [mailto:[email protected]] On Behalf Of 
> [email protected]
> Sent: Tuesday, September 11, 2007 10:12 PM
> To: [email protected]
> Subject: st: decomposition of Theil inequality measures
> Good evening, 
> I am trying to calculate Theil's inequality indices for 
> survey data and I have browsed the list of user written ado's 
> listed under "findit inequality" and "search inequality". 
> However, none of these commands seems to allow to break down 
> the Theil into its between- and within-group components. 
> Would anyone know commands that allow to do this? (I would be 
> interested in breakdowns by urban / rural strata as well as 
> by geographic/political regions) Please note that I am 
> working on simple cross sections for the time being. This 
> means that most ado's written for sectoral decompositions of 
> growth-inequality linkages do not apply to my case
> Many thanks!
> Best regards
> Borge Wietzke  
> Please access the attached hyperlink for an important 
> electronic communications disclaimer: 
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index