Some suggestions were made here:
http://www.statacorp.com/statalist/archive/2003-01/msg00693.html
http://www.statacorp.com/statalist/archive/2003-01/msg00695.html
I do not think the situation changed much since then -- I am not aware of a program for estimating inequality measures from grouped data specifically, or for fitting parametric distributions from grouped data (from which you could derive Gini estimates). Commands designed for use with unit-record data will assume equality within the income groups and therefore underestimate total inequality.
Philippe
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Eric Uslaner
> Sent: Thursday, September 25, 2008 8:52 PM
> To: [email protected]
> Subject: st: St: Inequality measures
>
> Hi,
>
> I have downloaded data on income categories over time by country. The
> categories are 9 deciles and then the top two quintiles. I have looked
> at various measures of inequality--and their associated help files--but
> I still can't figure out how to create a Gini index from these 11
> variables (income categories). Any suggestions would be appreciated.
>
> Thanks,
>
> Ric Uslaner
>
>
>
>
> *
> * 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/
