Forecasting Realized Volatility of Agricultural Commodity Futures with Infinite Hidden Markov HAR Models

Abstract

We construct a set of HAR models with three types of infinite Hidden Markov regime switching structures. Particularly, jumps, leverage effects, and speculation effects are taken into account in realized volatility modeling. We forecast five agricultural commodity futures (Corn, Cotton, Indica Rice, Palm oil and Soybean) based on high frequency data from Chinese futures markets and evaluate the forecast performances with both statistical and economic evaluation measures. The statistical evaluation results suggest that HAR models with infinite Hidden Markov regime switching structures have better precision compared the benchmark HAR models based on the MZ-R², MAFE, and MCS results. The economic evaluation results suggest that portfolios constructed with infinite Hidden Markov regime switching HARs achieve higher portfolio returns for risk averse investors compared to benchmark HAR model for short-term volatility forecasts.