by Andrey Fradkin
Abstract
We examine the informational content of historical and implied measures of variance through an evaluation of forecasts over horizons ranging from 1 to 22 days. These forecasts use heterogeneous autoregressive (HAR) regressions which are constructed with high-frequency data. Our results show that the t and forecasting ability of models based on historical realized variance (RV) increases with the addition of implied volatility in the regression model. We find that robust regression is better than OLS in forecasting RV outside of the estimation sample. The paper evaluates data from individual equities and the S&P 500.
Professor George Tauchen, Faculty Advisor
