Educating Ju-chang (Gini indeces etc)

elena spectra at elits.rousse.bg
Mon Sep 6 08:55:43 PDT 1999


Is this paper OK to use as an introduction? Slow downloading time (ab 20 minutes) It's a very educational experience, being on this list, yet although the dummies are a negligible minority here, please, guys, don't take our knowledge for granted when stupid questions are raised. Any info (even "a good introductory book" is damn hard to find - easier to do so on the Net). Another Dummy http://ideas.uqam.ca/ideas/data/Papers/wopkoelse9507.html Multivariate Gini Indices Koshevoy, G.A.

Mosler, K. (Seminar fuer Wirtschafts- und Sozialstatistik, Universitaet zu Koeln, Meister-Ekkehart-Str. 9/II, 0923 Koeln, Germany)

The Gini index and the Gini mean difference of a univariate distribution are extended to measure the disparity of a general $d$-variate distribution. We propose and investigate two approaches, one based on the distance of the distribution from itself, the other on the volume of a convex set in$(d+1)$-space, named the lift zonoid of the distribution. When $d=1$, this volume equals the area

between the usual Lorenz curve and the line of zero disparity, up to a scale factor. We get two

definitions of the multivariate Gini index, which are different (when $d > 1$) but connected through

the notion of the lift zonoid. Both notions inherit properties of the univariate Gini index, in

particular, they are vector scale invariant, continuous, bounded by $0$ and $1$, and the bounds

are sharp. They vanish if and only if the distribution is concentrated at one point. The indices have

a ceteris paribus property and are consistent with multivariate extensions of the Lorenz order.

Illustrations with data conclude the paper.

Creation: 1995 Keywords: Dilation; Disparity measurement; Gini mean difference; Lift zonoid; Lorenz order. Length: 21 pages Handle: RePEc:wop:koelse:9507

Paper provided by Universitaet zu Koeln in its series Statistics and Econometrics as number 7/95



More information about the lbo-talk mailing list