Bayesian Filtering for Jump-Diffusions With Application to Stochastic Volatility

摘要: In this article, the problem of sequentially learning parameters governing discretely observed jump-diffusions is explored. The estimation framework involves introduction latent points between every pair observations to allow a sufficiently accurate Euler–Maruyama approximation underlying (but unavailable) transition densities. Particle filtering algorithms are then implemented sample posterior distribution data and model online. methodology applied stochastic volatility (SV) with jumps. As well as using S&P 500 Index data, simulation study provided. Supplemental materials for article available