Title: Bayesian analysis of intraday stochastic volatility models with skew heavy-tailed error and smoothing spline seasonality
Authors: Teruo Nakatsuma - Keio University (Japan) [presenting]
Makoto Nakakita - Keio University (Japan)
Abstract: The aim is to extend the stochastic volatility (SV) model for application with intraday high frequency data of asset returns. It is well-known that intraday high frequency data of asset returns exhibit not only stylized characteristics (e.g., volatility clustering, heavy-tailed distribution) but also cyclical fluctuation in return volatility, which is called intraday seasonality. In a typical trading day, the volatility tends to be higher immediately after the opening or near the closing, but it tends to be lower in the middle of the trading hours. Our modeling strategy is two-fold. First, we model the intraday seasonality of return volatility with a B-spline polynomial and estimate it along with the stochastic volatility simultaneously. Second, we incorporate a possibly skew and heavy-tailed error distribution into the SV model by assuming that the error distribution belongs to a family of generalized hyperbolic (GH) distribution such as Laplace, variance-gamma and Student's $t$. We develop an efficient Markov chain Monte Carlo (MCMC) sampling algorithm for Bayesian inference of the proposed model and apply it to intraday data of Japanese stocks.