Copula-based regression models: A survey

In this review paper we collect several results about copula-based models, especially concerning regression models, by focusing on some insurance applications. (C) 2009 Elsevier B.V. All rights reserved.

An information-theoretic approach to statistical dependence: Copula information

We discuss the connection between information and copula theories by showing that a copula can be employed to decompose the information content of a multivariate distribution into marginal and dependence components, with the latter quantified by the mutual information. We define the information excess as a measure of deviation from a maximum-entropy distribution. The idea of marginal invariant dependence measures is also discussed and used to show that empirical linear correlation underestimates the amplitude of the actual correlation in the case of non-Gaussian marginals. The mutual information is shown to provide an upper bound for the asymptotic empirical log-likelihood of a copula. An analytical expression for the information excess of T-copulas is provided, allowing for simple model identification within this family. We illustrate the framework in a financial data set. Copyright (C) EPLA, 2009

Morphology and phylogenetic relationships of a remarkable new genus and two new species of Neotropical freshwater stingrays from the Amazon basin (Chondrichthyes: Potamotrygonidae)

The morphology and phylogenetic relationships of a new genus and two new species of Neotropical freshwater stingrays, family Potamotrygonidae, are investigated and described in detail. The new genus, Heliotrygon, n. gen., and its two new species, Heliotrygon gomesi, n. sp. (type-species) and Heliotrygon rosai, n. sp., are compared to all genera and species of potamotrygonids, based on revisions in progress. Some of the derived features of Heliotrygon include its unique disc proportions (disc highly circular, convex anteriorly at snout region, its width and length very similar), extreme subdivision of suborbital canal (forming a complex honeycomb-like pattern anterolaterally on disc), stout and triangular pelvic girdle, extremely reduced caudal sting, basibranchial copula with very slender and acute anterior extension, and precerebral and frontoparietal fontanellae of about equal width, tapering very little posteriorly. Both new species can be distinguished by their unique color patterns: Heliotrygon gomesi is uniform gray to light tan or brownish dorsally, without distinct patterns, whereas Heliotrygon rosai is characterized by numerous white to creamy-white vermiculate markings over a light brown, tan or gray background color. Additional proportional characters that may further distinguish both species are also discussed. Morphological descriptions are provided for dermal denticles, ventral lateral-line canals, skeleton, and cranial, hyoid and mandibular muscles of Heliotrygon, which clearly corroborate it as the sister group of Paratrygon. Both genera share numerous derived features of the ventral lateral-line canals, neurocranium, scapulocoracoid, pectoral basals, clasper morphology, and specific patterns of the adductor mandibulae and spiracularis medialis muscles. Potamotrygon and Plesiotrygon are demonstrated to share derived characters of their ventral lateral-line canals, in addition to the presence of angular cartilages. Our morphological phylogeny is further corroborated by a molecular phylogenetic analysis of cytochrome b based on four sequences (637 base pairs in length), representing two distinct haplotypes for Heliotrygon gomesi. Parsimony analysis produced a single most parsimonious tree revealing Heliotrygon and Paratrygon as sister taxa (boot-strap proportion of 70%), which together are the sister group to a clade including Plesiotrygon and species of Potamotrygon. These unusual stingrays highlight that potamotrygonid diversity, both in terms of species composition and undetected morphological and molecular patterns, is still poorly known.

A bivariate regression model for matched paired survival data: local influence and residual analysis

The use of bivariate distributions plays a fundamental role in survival and reliability studies. In this paper, we consider a location scale model for bivariate survival times based on the proposal of a copula to model the dependence of bivariate survival data. For the proposed model, we consider inferential procedures based on maximum likelihood. Gains in efficiency from bivariate models are also examined in the censored data setting. For different parameter settings, sample sizes and censoring percentages, various simulation studies are performed and compared to the performance of the bivariate regression model for matched paired survival data. Sensitivity analysis methods such as local and total influence are presented and derived under three perturbation schemes. The martingale marginal and the deviance marginal residual measures are used to check the adequacy of the model. Furthermore, we propose a new measure which we call modified deviance component residual. The methodology in the paper is illustrated on a lifetime data set for kidney patients.