Comparison of realized measure and implied volatility in forecasting volatility

摘要

This paper compares the information content of realized measures constructed from high-frequency data and implied volatilities from options in the context of forecasting volatility. The comparison is based on within-sample and out-of-sample (over horizons of 1-22 days) forecasts of daily S&P 500 index return volatility. The paper adds to the findings of previous studies, by considering recent developments in the related practice and the literature. It is shown that, for within-sample fitting, the realized measure is more informative than the implied volatility. In contrast, the implied volatility is more informative than the realized measure for out-of-sample forecasting, in particular for multi-step-ahead forecasting. Moreover, we show that it is helpful to use all the information provided by the realized measure and the implied volatility for the within-sample fitting. For multi-step-ahead forecasting, however, it is better to use only the implied volatility.