A0216
Title: When aggregate stock returns are negatively-skewed: International evidence
Authors: Kyu Ho Kang - Korea University (Korea, South) [presenting]
Kitak Kim - Korea University (Korea, South)
Abstract: A novel stochastic volatility model with time-varying skewness is proposed. The skewness is modeled by a split-normal return error, and the asymmetric error variance is assumed to follow a first-order Markov-switching process. We show that this modeling approach enables us to simulate the SV via one-block Gibbs sampling and demonstrate that our posterior sampling algorithm is reliable and efficient in simulation studies. According to our empirical applications to several aggregate stock return data, the aggregate returns exhibit negative skewness during normal periods. Meanwhile, the stock returns are symmetric during market crash episodes.