Hierarchical GARCH

29 Pages Posted: 23 Oct 2010 Last revised: 19 Dec 2015

See all articles by Christian T. Brownlees

Christian T. Brownlees

Universitat Pompeu Fabra - Faculty of Economic and Business Sciences

Date Written: December 18, 2015

Abstract

There is strong empirical evidence that the GARCH estimates obtained from panels of financial time series cluster. In order to capture this empirical regularity, this paper introduces the Hierarchical GARCH (HG) model. The HG is a nonlinear panel specification in which the coefficients of each series are modeled as a function of observed series characteristic and an unobserved random effect. A joint panel estimation strategy is proposed to carry out inference for the model. A simulation study shows that when there is a strong degree of coefficient clustering panel estimation leads to substantial accuracy gains in comparison to estimating each GARCH individually. The HG is applied to a panel of U.S. financial institutions in the 2007-2009 crisis, using firm size and leverage as characteristics. Results show evidence of coefficient clustering and that the characteristics capture a significant portion of cross sectional heterogeneity. An out-of-sample volatility forecasting application shows that when the sample size is modest coefficient estimates based on the panel estimation approach perform better than the ones based on individual estimation.

Keywords: Panel GARCH, Nonlinear Panel, Random Effects, Volatility

JEL Classification: C31, C32, C33

Suggested Citation

Brownlees, Christian T., Hierarchical GARCH (December 18, 2015). Available at SSRN: https://ssrn.com/abstract=1695649 or http://dx.doi.org/10.2139/ssrn.1695649

Christian T. Brownlees (Contact Author)

Universitat Pompeu Fabra - Faculty of Economic and Business Sciences ( email )

Ramon Trias Fargas 25-27
Barcelona, 08005
Spain

HOME PAGE: http://econ.upf.edu/~cbrownlees/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
613
Abstract Views
3,260
Rank
80,604
PlumX Metrics