Parameter Estimation and Applications for Stochastic Volatility Model with Time-Varying Leverage Effect

To effectively capture the time-varying asymmetry of leverage effects in financial time series, this paper introduces a semi-parametric stochastic volatility model incorporating time-varying leverage effects based on linear splines. The parameters of this model are estimated using the Bayesian Markov Chain Monte Carlo (MCMC) method. Simulation studies indicate that the Bayesian MCMC method performs well in parameter estimation for the proposed model, even with limited sample sizes. Finally, the suggested semi-parametric stochastic volatility model with time-varying leverage effects is applied to the empirical analysis of daily returns data for the Shanghai Composite Index and the Shenzhen Component Index from January 4, 2000, to August 18, 2020. The results demonstrate the superiority of the proposed method.