Realised Volatility Forecasts for Stock Index Futures Using the HAR Models with Bayesian Approaches *

Abstract

We investigate the realised volatility (RV) forecasts for the short, mid, and long term by developing the HAR models with Bayesian approaches and employing the high-frequency data of the China Stock Index 300 (CSI300) future for the period from 16 April 2010 to 21 May 2014. We also evaluate the performances of competing models for both in-sample forecasts and out-of-sample forecasts. We find that the proposed HAR-type models with Bayesian approaches capture the time-varying properties of parameters and predictor sets. We also find that the HAR-type models with Bayesian approaches have superior forecast performance for both in-sample forecasts and out-of-sample forecasts as compared with the benchmark HAR-type models.