Concordance and ginfs measure of association
Author:
Roger B. Nelsen a
| Affiliation: | a Department of Mathematical Sciences, Lewis and Clark College, Portland, OR |
DOI:
10.1080/10485259808832744
Publication Frequency:
8 issues per year
Subjects:
Mathematical Economics;
Mathematical Finance;
Medical Statistics;
Statistical Theory & Methods;
Statistics;
Statistics for the Biological Sciences;
Stochastic Models & Processes;
Formats available:
PDF
(English)
View Article:
View Article (PDF)
Abstract
We study the relationship between concordance and the population version γ of Gini's rank correlation coefficient. For a pair
X, Y) of continuous random variables, we show that γ is a function of probabilities of concordance and discordance between (X, Y) and pairs with the same margins but whose joint distributions are the Fr chet upper and lower bounds. We also show that γ depends only on the diagonal and secondary diagonal sections of the copula of (X, Y) and present corresponding results for the sample statistic.
|
| Keywords: Concordance; copulas; Gini's rank correlation coefficient; Frechet bounds; Kendall's tau; measures of association; Spearman's footrule; Spearman's rho |
| AMS 1991 Subject ClassiJication: Primary: 62H20; Secondary: 62E10; 62HOS |
| view references (13) |

Download Citation


X, Y) of continuous random variables, we show that γ is a function of probabilities of concordance and discordance between (X, Y) and pairs with the same margins but whose joint distributions are the Fr
chet upper and lower bounds. We also show that γ depends only on the diagonal and secondary diagonal sections of the copula of (X, Y) and present corresponding results for the sample statistic.
CiteULike
Del.icio.us
BibSonomy
Connotea