Efficient factor GARCH models and factor-DCC models
- 11 February 2009
- journal article
- research article
- Published by Taylor & Francis Ltd in Quantitative Finance
- Vol. 9 (1), 71-91
- https://doi.org/10.1080/14697680802039840
Abstract
We report that, in the estimation of univariate GARCH or multivariate generalized orthogonal GARCH (GO-GARCH) models, maximizing the likelihood is equivalent to making the standardized residuals as independent as possible. Based on this, we propose three factor GARCH models in the framework of GO-GARCH: independent-factor GARCH exploits factors that are statistically as independent as possible; factors in best-factor GARCH have the largest autocorrelation in their squared values such that their volatilities could be forecast well by univariate GARCH; and factors in conditional-decorrelation GARCH are conditionally as uncorrelated as possible. A convenient two-step method for estimating these models is introduced. Since the extracted factors may still have weak conditional correlations, we further propose factor-DCC models as an extension to the above factor GARCH models with dynamic conditional correlation (DCC) modelling the remaining conditional correlations between factors. Experimental results for the Hong Kong stock market show that conditional-decorrelation GARCH and independent-factor GARCH have better generalization performance than the original GO-GARCH, and that conditional-decorrelation GARCH (among factor GARCH models) and its extension with DCC embedded (among factor-DCC models) behave best.Keywords
This publication has 33 references indexed in Scilit:
- CAViaRJournal of Business & Economic Statistics, 2004
- Forecasting Volatility in Financial Markets: A ReviewJournal of Economic Literature, 2003
- A Multivariate Generalized Autoregressive Conditional Heteroscedasticity Model With Time-Varying CorrelationsJournal of Business & Economic Statistics, 2002
- Dynamic Conditional CorrelationJournal of Business & Economic Statistics, 2002
- Blind source separation by nonstationarity of variance: a cumulant-based approachIEEE Transactions on Neural Networks, 2001
- Quasi-nonparametric blind inversion of Wiener systemsIEEE Transactions on Signal Processing, 2001
- A test for independence based on the correlation dimensionEconometric Reviews, 1996
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Quasi-maximum likelihood estimation and inference in dynamic models with time-varying covariancesEconometric Reviews, 1992
- Generalized autoregressive conditional heteroskedasticityJournal of Econometrics, 1986