< Back to previous page

Publication

Robust M-estimation of multivariate GARCH models

Journal Contribution - Journal Article

In empirical work on multivariate ¯nancial time series, it is com-
mon to postulate a Multivariate GARCH model. We show that the
popular Gaussian quasi-maximum likelihood estimator of MGARCH
models is very sensitive to outliers in the data. We propose to use ro-
bust M-estimators and provide asymptotic theory for M-estimators of
MGARCH models. The Monte Carlo study and empirical application
document the good robustness properties of the M-estimator with a fat-
tailed Student t loss function and volatility models with the property of
bounded innovation propagation.
Journal: Computational Statistics and Data Analysis
ISSN: 0167-9473
Volume: 54
Pages: 2459-2469
Publication year:2010
Keywords:GARCH models, M-estimators, multivariate time series, robust methods
  • Scopus Id: 77955278346