Improved rank-based dependence measures for categorical data

• Published in: Statistics & probability letters Vol. 63; no. 2; pp. 157 - 163
• Main Authors: Vandenhende, François, Lambert, Philippe
• Format: Journal Article Web Resource
• Language: English
• Published: Amsterdam Elsevier B.V 15.06.2003; Elsevier; Elsevier Science
• Series: Statistics & Probability Letters
• Subjects: Bivariate ordinal data; Bivariate ordinal data Dependence Copula Goodness-of-fit test; Copula; Dependence; Exact sciences and technology; Goodness-of-fit test; Mathematics; Mathématiques; Nonparametric inference; Parametric inference; Physical, chemical, mathematical & earth Sciences; Physique, chimie, mathématiques & sciences de la terre; Probability and statistics; Sciences and techniques of general use; Statistics; Copula; Goodness-of-fit test; Bivariate ordinal data; Dependence; Statistical method; Categorical data; Goodness of fit test; Bootstrap

We extend rank-based dependence measures like Spearman's rho to categorical data so that the same ±1 limits are always reached under complete dependence. A goodness-of-fit procedure is derived for dependence models using copulas.