Bayesian inference of multivariate-GARCH-BEKK models
The main aim of this paper is to present a Bayesian analysis of Multivariate GARCH(l, m) (M-GARCH) models including estimation of the coefficient parameters as well as the model order, by combining a set of existing MCMC algorithms in the literature. The proposed algorithm focuses on the BEKK formul...
| Main Authors: | , |
|---|---|
| Format: | Journal Article |
| Published: |
Springer Nature
2022
|
| Online Access: | http://hdl.handle.net/20.500.11937/89416 |
| _version_ | 1848765214771642368 |
|---|---|
| author | Livingston, Jr, Glen Nur, Darfiana |
| author_facet | Livingston, Jr, Glen Nur, Darfiana |
| author_sort | Livingston, Jr, Glen |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | The main aim of this paper is to present a Bayesian analysis of Multivariate GARCH(l, m) (M-GARCH) models including estimation of the coefficient parameters as well as the model order, by combining a set of existing MCMC algorithms in the literature. The proposed algorithm focuses on the BEKK formulation of the multivariate GARCH model. The estimation procedure will be designed as a custom MCMC with embedded Reversible Jump MCMC (RJMCMC) and Delayed Rejection Metropolis-Hastings (DRMH) steps implemented using the statistical software R. The RJMCMC steps allow three variants of BEKK models (constant, diagonal and full) to be indexed and this index included as a parameter to be estimated. The proposed MCMC algorithms are validated using extensive simulation experiments followed by a case study using bivariate data derived from the daily share prices for BHP Group Limited, Rio Tinto Group, and Fortescue Metals Group Limited on the ASX over from September 2013 to December 2021. |
| first_indexed | 2025-11-14T11:31:42Z |
| format | Journal Article |
| id | curtin-20.500.11937-89416 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:31:42Z |
| publishDate | 2022 |
| publisher | Springer Nature |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-894162022-10-24T05:43:17Z Bayesian inference of multivariate-GARCH-BEKK models Livingston, Jr, Glen Nur, Darfiana The main aim of this paper is to present a Bayesian analysis of Multivariate GARCH(l, m) (M-GARCH) models including estimation of the coefficient parameters as well as the model order, by combining a set of existing MCMC algorithms in the literature. The proposed algorithm focuses on the BEKK formulation of the multivariate GARCH model. The estimation procedure will be designed as a custom MCMC with embedded Reversible Jump MCMC (RJMCMC) and Delayed Rejection Metropolis-Hastings (DRMH) steps implemented using the statistical software R. The RJMCMC steps allow three variants of BEKK models (constant, diagonal and full) to be indexed and this index included as a parameter to be estimated. The proposed MCMC algorithms are validated using extensive simulation experiments followed by a case study using bivariate data derived from the daily share prices for BHP Group Limited, Rio Tinto Group, and Fortescue Metals Group Limited on the ASX over from September 2013 to December 2021. 2022 Journal Article http://hdl.handle.net/20.500.11937/89416 10.1007/s00362-022-01360-6 http://creativecommons.org/licenses/by/4.0/ Springer Nature fulltext |
| spellingShingle | Livingston, Jr, Glen Nur, Darfiana Bayesian inference of multivariate-GARCH-BEKK models |
| title | Bayesian inference of multivariate-GARCH-BEKK models |
| title_full | Bayesian inference of multivariate-GARCH-BEKK models |
| title_fullStr | Bayesian inference of multivariate-GARCH-BEKK models |
| title_full_unstemmed | Bayesian inference of multivariate-GARCH-BEKK models |
| title_short | Bayesian inference of multivariate-GARCH-BEKK models |
| title_sort | bayesian inference of multivariate-garch-bekk models |
| url | http://hdl.handle.net/20.500.11937/89416 |