Realized Range Volatility Forecasting: Dynamic Features and Predictive Variables

In this paper, we estimate, model and forecast realized range volatility, a realized measure and estimator of the quadratic variation of financial prices. This quantity was introduced early in the literature and it is based on the high–low range observed at high frequency during the day. We consider the impact of the microstructure noise in high frequency data and correct our estimations, following a known procedure. Then, we model the realized range accounting for the well-known stylized effects present in financial data and we investigate the role that macroeconomic and financial variables play when forecasting daily stocks volatility. We consider an HAR model with asymmetric effects with respect to the volatility and the return, and GARCH and GJR specifications for the variance equation. Moreover, we consider a non-Gaussian distribution for the innovations. Finally, we extend the model including macroeconomic and financial variables that capture the present and the future state of the economy. We find that these variables are significantly correlated with the first common component of the volatility series and they have a highly in-sample explanatory power. The analysis of the forecast performance in 16 NYSE stocks suggests that the introduction of asymmetric effects with respect to the returns and the volatility in the HAR model result in a significant improvement in the point forecasting accuracy as well and the variables related with the U.S. stock market performance and proxies for the credit risk.