The Scod Model: Analyzing Durations with a Semiparametric Copula Approach

Abstract

This paper applies a new methodology for modeling order durations of ultra-high-frequency data using copulas. While the class of common Autoregressive Conditional Duration models are characterized by strict parameterizations and high computational burden, the semiparametric copula approach proposed here offers more flexibility in modeling the dynamic duration process by separating the marginal distributions of waiting times from their temporal dependence structure. Comparing both frameworks as to their density forecast abilities, the Semiparametric Copula Duration model clearly shows a better performance.