Abstract

Copula modeling has become an increasingly popular tool in finance to model assets returns dependency. In essence, copulas enable us to extract the dependence structure from the joint distribution function of a set of random variables and, at the same time, to isolate such dependence structure from the univariate marginal behavior. In this study, based on US stock data, we illustrate how tail-dependency tests may be misleading as a tool to select a copula that closely mimics the dependency structure of the data. This problem becomes more severe when the data is scaled by conditional volatility and/or filtered out for serial correlation. The discussion is complemented, under more general settings, with Monte Carlo simulations and portfolio management implications. © 2008 Elsevier Ltd. All rights reserved.