Re: : st: RE: Gini coefficient for spatial data

[Francisco Rowe <frowe@ucn.cl>]

Thanks Stephen. 
Your guesses are correct. I am considering inequality measurements for (b) -in reference to the possibilities you listed below.
I think, with the information that I got from you and Nick, my doubts were cleared.

Cheers,

Francisco.

On 24/05/2012, at 1:17 AM, <S.Jenkins@lse.ac.uk> <S.Jenkins@lse.ac.uk> wrote:

> The fundamental issues appear to be: (1) what is the unit across which
> you wish to measure inequality? (2) What units are your data observed
> in?  Francisco needs to clarify this.
> 
> Suppose individuals live in areas and your outcome variable is 'income'
> 
> Possibilities include:
> (a) you want inequality across all individuals, but you only observe the
> average income for each area
> (b) you want inequality across all areas, but you only observe the
> average income for each area
> 
> In (b) the unit and observation level coincide; in (a), they don't. 
> 
> If (a) is of interest, it must be the case that inequality among
> individuals in the population is under-estimated.
> 
> Recall that, for generalised entropy inequality measures, one can write
> 
> Total inequality = I_B  + I_W
> 
> I_B is Within-groups inequality = weighted sum of the inequalities for
> each group (region!), where the weights depend, in general, on the
> group's income share and their population share
> 
> I_W is between-groups inequality = total inequality there would be were
> each individual to receive the mean income of the group to which they
> belong
> 
> [For more details, see the References in -ineqdeco- or -indeqec0- on
> SSC]
> 
> If case (a) applies to you, and you simply apply the programs cited, you
> will miss out I_W. 
> 
> If this is a serious problem, then you will have to make some
> assumptions (or use external information) about the distribution of
> income within regions.
> 
> Stephen
> 
> ------------------------------
> 
> Date: Wed, 23 May 2012 08:49:13 +1000
> From: Francisco Rowe <frowe@ucn.cl>
> Subject: Re: st: RE: Gini coefficient for spatial data
> 
> Thanks Nick.
> 
> Well, I rephrase my question: Can I apply the existing Stata commands
> -e.g. ineqdeco, inequal, sgini- to calculate the Gini coefficient using
> spatial data? All of the commands I mentioned seem to require as input
> micro data. 
> 
> What I want is to measure the degree of concentration/dispersion of
> different variables at the different geographical scales.
> 
> Francisco.
> 
> 
> 
> Stephen
> ------------------
> Professor Stephen P. Jenkins <s.jenkins@lse.ac.uk>
> Department of Social Policy and STICERD
> London School of Economics and Political Science
> Houghton Street, London WC2A 2AE, UK
> Tel: +44(0)20 7955 6527
> Changing Fortunes: Income Mobility and Poverty Dynamics in Britain, OUP
> 2011, http://ukcatalogue.oup.com/product/9780199226436.do
> Survival Analysis Using Stata:
> http://www.iser.essex.ac.uk/survival-analysis
> Downloadable papers and software: http://ideas.repec.org/e/pje7.html
> 
> 
> Please access the attached hyperlink for an important electronic communications disclaimer: http://lse.ac.uk/emailDisclaimer
> 
> *
> *   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/