Matrix exponential stochastic volatility with cross leverage

详细信息    查看全文

• 作者：Tsunehiro Ishihara^a ; ^{T.Ishihara@r.hit-u.ac.jp" class="auth_mail" title="E-mail the corresponding author} ; Yasuhiro Omori^b ; ^{omori@e.u-tokyo.ac.jp" class="auth_mail" title="E-mail the corresponding author} ; Manabu Asai^c ; ^{m-asai@soka.ac.jp" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Dynamic correlation ; Leverage effect ; Matrix exponential ; Markov chain Monte Carlo ; Multi-move sampler ; Multivariate stochastic volatility
• 刊名：Computational Statistics & Data Analysis
• 出版年：2016
• 出版时间：August 2016
• 年：2016
• 卷：100
• 期：Complete
• 页码：331-350
• 全文大小：1115 K

文摘

A multivariate stochastic volatility model with the dynamic correlation and the cross leverage effect is described and its estimation using Markov chain Monte Carlo is proposed. The time-varying covariance matrices are guaranteed to be positive definite by using a matrix exponential transformation. Of particular interest is our approach for sampling a set of latent matrix logarithm variables from their conditional posterior distribution, where we construct the proposal density based on an approximating linear Gaussian state space model. The proposed model and its extensions with fat-tailed error distribution are applied to trivariate returns data (daily stocks, bonds, and exchange rates) of Japan. Further, a model comparison is conducted including constant correlation multivariate stochastic volatility models with leverage and diagonal multivariate GARCH models.