CMStatistics 2017: Start Registration
View Submission - CFE
A1762
Title: Realized stochastic volatility with skew-t error Authors:  Makoto Takahashi - Osaka University (Japan) [presenting]
Yasuhiro Omori - University of Tokyo (Japan)
Toshiaki Watanabe - Hitotsubashi University (Japan)
Abstract: The realized stochastic volatility model with Student's t error is extended to the skew-t error model by using the mixture representation of the skew-t distribution. This representation, including normal, Student's t, and skew-normal distributions as special cases, allows flexible modeling of the skewness and heavy tails in the conditional distribution of financial asset returns. The Bayesian estimation scheme via a Markov chain Monte Carlo method is developed and the empirical results using the US and Japanese stock indices will be presented.