Bayesian clustering of many GARCH models
Preprint
- 28 November 2003
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
We consider the estimation of a large number of GARCH models, of the order of several hundreds. To achieve parsimony, we classify the series in a small number of groups. Within a cluster, the series share the same model and the same parameters. Each cluster contains therefore similar series. We do not know a priori which series belongs to which cluster. The model is a finite mixture of distributions, where the component weights are unknown parameters and each component distribution has its own conditional mean and variance. Inference is done by the Bayesian approach, using data augmentation techniques. Illustrations are provided.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Multivariate GARCH Models: A SurveySSRN Electronic Journal, 2003
- Dynamic Conditional CorrelationJournal of Business & Economic Statistics, 2002
- Markov chain Monte Carlo Estimation of Classical and Dynamic Switching and Mixture ModelsJournal of the American Statistical Association, 2001
- Bayesian analysis of cross-section and clustered data treatment modelsJournal of Econometrics, 2000
- Bayesian Inference in Dynamic Econometric ModelsPublished by Oxford University Press (OUP) ,2000
- Markov Chain Monte Carlo Convergence Diagnostics: A Comparative ReviewJournal of the American Statistical Association, 1996
- Marginal Likelihood from the Gibbs OutputJournal of the American Statistical Association, 1995
- Multivariate Simultaneous Generalized ARCHEconometric Theory, 1995
- Estimation of Finite Mixture Distributions Through Bayesian SamplingJournal of the Royal Statistical Society Series B: Statistical Methodology, 1994
- Modelling the Coherence in Short-Run Nominal Exchange Rates: A Multivariate Generalized Arch ModelThe Review of Economics and Statistics, 1990