Discrete-Time Stochastic Volatility Models and MCMC-Based Statistical Inference
25 Pages Posted: 1 Nov 2008
Date Written: October 30, 2008
In this paper, we review the most common specifications of discrete-time stochastic volatility (SV) models and illustrate the major principles of corresponding Markov Chain Monte Carlo (MCMC) based statistical inference. We provide a hands-on approach which is easily implemented in empirical applications and financial practice and can be straightforwardly extended in various directions. We illustrate empirical results based on different SV specifications using returns on stock indices and foreign exchange rates.
Keywords: Stochastic Volatility, Markov Chain Monte Carlo, Metropolis-Hastings algorithm, Jump Processes
JEL Classification: C15, C22, G12
Suggested Citation: Suggested Citation