Work

Variance Targeting Estimation of Multivariate GARCH Models

Year: 2014

Type: article

Abstract: We establish the strong consistency and the asymptotic normality (CAN) of the variance-targeting estimator (VTE) of the parameters of the multivariate CCC-GARCH(p, q) processes. This method alleviates the numerical difficulties encountered in the maximization of the quasi-likelihood by using an estimator of the unconditional variance. It is shown that the distribution of the VTE can be consistently estimated by a simple residual bootstrap technique. We also use the VTE for testing the model adequacy. A test statistic in the spirit of the score test is constructed, and its asymptotic properties are derived under the null assumption that the model is well specified. An extension of the VT method to asymmetric CCC-GARCH models incorporating leverage effects is studied. Numerical illustrations are provided and an empirical application based on daily exchange rates is proposed.

Source: Journal of Financial Econometrics

DOI: 10.1093/jjfinec/nbu030

Authors: Christian Francq, Lajos Horváth, Jean-Michel Zakoïan

Institutions: Université de Lille, Centre de Recherche en Économie et Statistique, Institut Polytechnique de Paris

Language: English

Topic: Financial Risk and Volatility Modeling

Subfield: Finance

Field: Economics, Econometrics and Finance

Domain: Social Sciences

Open Access status: green

Funders: National Science Foundation, Agence Nationale de la Recherche, Economic and Social Research Council

Awards: G3798960987, Probabilistic approach to assessing macroeconomic uncertainties, G7240651115, Statistical Inference for Functional and High-Dimensional Time Series