Forecasting Realised Volatility: A Markov Switching Approach with Time‐Varying Transition Probabilities

Abstract

This paper introduces a markov‐switching heterogeneous autoregressive (MS‐HAR) model with time‐varying transition probabilities (TVTP) for the realised volatility of Shanghai securities composite index returns. Its various extensions have been obtained by including negative returns outside trading hours in addition to the leverage effects and trading volume. The findings show asymmetries in the impact of explanatory variables on the realised volatility. Moreover, the out‐of‐sample results show that the benchmark MS‐HAR with TVTP model and its extensions consistently outperform the simple HAR model, MS‐HAR model with constant transition probabilities (CTP) and their extensions. These results are robust to alternative realised measurements, and have economic implications.