Forecast the realized range-based volatility: The role of investor sentiment and regime switching

Abstract

In this study, we first investigate the impacts of investor sentiment on the realized range-based volatility in the framework of regime switching model. Out-of-sample results show that investor sentiment can significantly improve the forecasting performance of volatility models. Moreover, the results further find that combining the regime switching of those models with investor sentiment can substantially gain higher forecasting accuracy. Our conclusions are robust to different forecasting windows.