A multivariate GARCH model with an infinite hidden Markov mixture

This paper proposes a new Bayesian semiparametric model that combines a multivariate GARCH (MGARCH) component and an infinite hidden Markov model. The new model nonparametrically approximates both the shape of unknown returns distributions and their short-term evolution. It also captures the smooth trend of the second moment with the MGARCH component and the potential skewness, kurtosis, and volatility roughness with the Bayesian nonparametric component. The results show that this more-sophisticated econometric model not only has better out-of-sample density forecasts than benchmark models, but also provides positive economic gains for a CRRA investor at different risk-aversion levels when transaction costs are assumed. After considering the transaction costs, the proposed model dominates all benchmark models/portfolios when No Short-Selling or No Margin-Trading restriction is imposed.