Structural Breaks and Time Variation in High-Dimensional Dependencies

CDS members associated with the project: Prof. Dr. Dominik Wied

This (DFG-funded) project from the field of statistics and econometrics is concerned with dependencies of financial returns. In economics and finance, the goal is to model dependencies as accurately as possible in order to construct suitable portfolios, to forecast portfolio risk or to measure contagion effects.

The focus of our project lies on modeling dependencies with copula models. These models allow for separating dependencies and marginal distributions resulting in considerable flexibility, which permits applications in distinct research fields. Moreover, the models allow for nonlinear dependencies of various forms, in particular dependencies of extremes and asymmetric dependence structures.

The last few years brought two important developments in the copula literature. First, many models allow for time-varying dependencies. Second, several models allow for flexible dependencies in more than two dimensions. The aim of this project is to develop methods which lie at the intersection of these two developments. In particular, we are advancing the analysis of tests for structural breaks with a huge number of variables, where we focus on factor copula models. The basic question is whether it is necessary to model time-varying dependencies in a complex way or whether, e.g., a model with a single breakpoint is sufficient. We are developing appropriate testing methods for both retrospective analyses and online monitoring, derive theoretical properties and apply the methods on various financial returns.

Reference:

• H. Manner, F. Stark, D. Wied. Testing for Structural Breaks in Factor Copula Models, Journal of Econometrics, 208(2), 324–345, 2019