How Can Long Memory in Volatility Be Eliminated in Portfolio Optimization: An Empirical Evidence Using Copulas

Abstract

This paper focuses on the analysis of long-memory properties of copula-based time series. We empirically investigate the relation between copulas parameter modeling temporal dependence and dependence structure, using simulated and financial series. Our results prove the existence of a positive relation relying two Markov process th X + and th Y + to their dependence structure.