A1475
Title: A HAR-based stochastic volatility model for leverage propagation
Authors: Helena Veiga - Uned (Spain) [presenting]
J Miguel Marin - University Carlos III (Spain)
Eva Romero - Universidad Complutense de Madrid (Spain)
Abstract: The aim is to propose a stochastic volatility model that uses a heterogeneous autoregressive process to capture the persistence of leverage over time. The properties of the model are analyzed by simulation in terms of leverage and leverage propagation using a recent concept in the field, and it is found that the model can generate both effects. Data cloning is also introduced for parameter estimation, which provides accuracy and computational efficiency in finite samples. Empirical analysis shows the proposal has good in-sample and out-of-sample performances across different financial return series. This makes it an effective and simple tool for capturing leverage dynamics in financial markets.
