Yasuhiro Omori

Overview

Yasuhiro Omori is an econometrician at the Faculty of Economics, University of Tokyo. He is best known for extending the Kim-Shephard-Chib (1998) multi-move MCMC sampler to SV models with leverage by approximating the joint density of log-squared return and volatility innovations with a 10-component bivariate Gaussian mixture (Omori, Chib, Shephard, and Nakajima 2007). He has also developed block samplers for asymmetric SV models (Omori-Watanabe 2008) and methods for simultaneous estimation from daily returns and realized volatility (Takahashi-Omori-Watanabe 2009).

Key Contributions

• Omori-Chib-Shephard-Nakajima (2007): Jointly with Siddhartha Chib, Neil Shephard, and Jouchi Nakajima; 10-component bivariate normal mixture approximation for the joint density of $(\varepsilon_t^*, \eta_t \mid d_t)$ — the key insight that leverage information is recoverable via $d_t = \text{sign}(y_t)$ and the analytically derived mean-square-optimal linearization coefficients $a_j = e^{v_j^2/8}$, $b_j = \tfrac{1}{2}e^{v_j^2/8}$; enables the Gaussian simulation smoother to handle $\rho \neq 0$; TOPIX (1998–2002) log Bayes factor ASV vs. SV $\approx 2.24$ — leverage decisively present. See Stochastic Volatility and Omori-Chib-Shephard-Nakajima (2007).

Related

• Stochastic Volatility
• Siddhartha Chib
• Neil Shephard
• Jouchi Nakajima
• Omori-Chib-Shephard-Nakajima (2007)
• Kim-Shephard-Chib (1998)