Flexible Modelling of Dependence in Volatility Processes

Abstract

This paper proposes a novel volatility model that draws from the existing literature on autoregressive stochastic volatility models, aggregation of autoregressive processes, and Bayesian nonparametric modelling to create a dynamic SV model that can explain long range dependence. The volatility process is assumed to be the aggregate of autoregressive processes where the distribution of the autoregressive coefficients is modelled using a flexible Bayesian approach. The model provides insight into the dynamic properties of the process. An efficient algorithm is defined which uses recently proposed adaptive Monte Carlo methods. The proposed model is applied to the daily returns of stock indices.