A Forecast Based Comparison of Restricted Realized Covariance Models

Abstract

Models for realized covariance matrices may suffer for the curse of dimensionality as more traditional multivariate volatility models(such as GARCH and stochastic volatility). Within the class of realized covariance models we focus on the Wishart specification introduced by Gourieroux et al. (2009) and analyze here the forecasting performances of the parametric restrictions discussed in Bonato et al. (2009) which are motivated by asset features such as their economic sector, book-to-market or price-earnings ratios, among others. Our purpose is to verify if restricted model forecasts are statistically equivalent to full model specification, a result that would support the use of restrictions when the problem cross sectional dimension is large.

Keywords: Realized covariance, WAR, HAR, multivariate volatility forecasts

JEL Classification: C32, C53, C52