Volatility forecasting using threshold heteroskedastic models of the intra-day range

This paper provides an effective approach for forecasting return volatility via threshold heteroskedastic models of the daily asset price range, defined as the difference between the highest and lowest log asset price recorded throughout the day. We propose a general model specification, allowing the intra-day high-low price range to depend nonlinearly on past information, or an exogenous variable such as US market information. The model captures aspects such as asymmetry and heteroskedasticity commonly observed in financial markets. We focus on parameter estimation, inference and volatility forecasting in a Bayesian framework. An MCMC sampling scheme is employed for estimation and shown to work well in simulation experiments. Finally, we compare competing range-based and returnbased heteroskedastic models via out-of-sample forecast performance. Applied to six international financial market indices, the range-based threshold heteroskedastic model is well supported by the data in terms of finding significant threshold nonlinearity, diagnostic checking and volatility forecast performance under various volatility proxies.