Title: On the asymmetric impact of macro-variables on volatility
Authors: Alessandra Amendola - University of Salerno (Italy)
Giampiero Gallo - NYU in Florence (Italy)
Vincenzo Candila - University of Salerno (Italy) [presenting]
Abstract: The GARCH-MIDAS model is extended to take into account possible different impacts from positive and negative macroeconomic variations on financial market volatility. We evaluate the proposed specification by a Monte Carlo simulation which shows good estimation properties with the increase in the sample size. The empirical application is performed on the daily S\&P 500 realized volatility dynamics with the monthly industrial production as an additional (signed) determinant. In the out-of-sample analysis, our asymmetric GARCH-MIDAS model statistically outperforms the competing specifications, represented by the GARCH(1,1), GJR-GARCH and GARCH-MIDAS models.