dorsal/arxiv
View SchemaBayesian Analysis of the Conditional Correlation Between Stock Index Returns with Multivariate SV Models
| Authors | Anna Pajor |
|---|---|
| Categories | |
| ArXiv ID | physics/0607176 |
| URL | https://arxiv.org/abs/physics/0607176 |
Abstract
In the paper we compare the modelling ability of discrete-time multivariate Stochastic Volatility models to describe the conditional correlations between stock index returns. We consider four trivariate SV models, which differ in the structure of the conditional covariance matrix. Specifications with zero, constant and time-varying conditional correlations are taken into account. As an example we study trivariate volatility models for the daily log returns on the WIG, SP500, and FTSE100 indexes. In order to formally compare the relative explanatory power of SV specifications we use the Bayesian principles of comparing statistic models. Our results are based on the Bayes factors and implemented through Markov Chain Monte Carlo techniques. The results indicate that the most adequate specifications are those that allow for time-varying conditional correlations and that have as many latent processes as there are conditional variances and covariances. The empirical results clearly show that the data strongly reject the assumption of constant conditional correlations.
{
"annotation_id": "91fcef6c-ba2b-4d60-a4ee-ef3df84029bb",
"date_created": "2026-03-02T18:01:10.252000Z",
"date_modified": "2026-03-02T18:01:10.252000Z",
"file_hash": "1c84234fafe2de03c06d63e299a4464d820581a3d18b5bab1dac17cd2505f0ec",
"private": false,
"record": {
"abstract": "In the paper we compare the modelling ability of discrete-time multivariate\nStochastic Volatility models to describe the conditional correlations between\nstock index returns. We consider four trivariate SV models, which differ in the\nstructure of the conditional covariance matrix. Specifications with zero,\nconstant and time-varying conditional correlations are taken into account. As\nan example we study trivariate volatility models for the daily log returns on\nthe WIG, SP500, and FTSE100 indexes. In order to formally compare the relative\nexplanatory power of SV specifications we use the Bayesian principles of\ncomparing statistic models. Our results are based on the Bayes factors and\nimplemented through Markov Chain Monte Carlo techniques. The results indicate\nthat the most adequate specifications are those that allow for time-varying\nconditional correlations and that have as many latent processes as there are\nconditional variances and covariances. The empirical results clearly show that\nthe data strongly reject the assumption of constant conditional correlations.",
"arxiv_id": "physics/0607176",
"authors": [
"Anna Pajor"
],
"categories": [
"physics.data-an",
"q-fin.ST"
],
"title": "Bayesian Analysis of the Conditional Correlation Between Stock Index Returns with Multivariate SV Models",
"url": "https://arxiv.org/abs/physics/0607176"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "847b3516-b49c-4916-b844-30733016a94d",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}