Volatility Feedback and Risk Premium in GARCH Models with Generalized Hyperbolic Distributions

Abstract

The mixture structure of the generalized hyperbolic distribution of Barndorff-Nielsen (1997) is explored to quantify the contemporaneous correlation between return and volatility and to identify the effects of volatility feedback and risk premium within GARCH models. The statistical analysis of FTSE 100 and S&P 500 index excess return series supports both volatility feedback and risk premium theories.

Keywords: Contemporaneous correlation, ARCH-M decomposition, mixture distributions, NIG distribution, GH skewed t distribution, maximum likelihood

JEL Classification: C22, C51