SEARCH

SEARCH BY CITATION

Keywords:

  • Dirichlet process prior;
  • long memory;
  • Markov chain Monte Carlo;
  • Metropolis–Hastings;
  • semiparametric;
  • stochastic volatility;
  • wavelets
  • C11;
  • C14;
  • C22

Abstract.  In this paper, a semiparametric, Bayesian estimator of the long-memory stochastic volatility model's fractional order of integration is presented. This new estimator relies on a highly efficient, Markov chain Monte Carlo (MCMC) sampler of the model's posterior distribution. The MCMC algorithm is set forth in the time-scale domain of the stochastic volatility model's wavelet representation. The key to and centerpiece of this new algorithm is the quick and efficient multi-state sampler of the latent volatility's wavelet coefficients. A multi-state sampler of the latent wavelet coefficients is only possible because of the near-independent multivariate distribution of the long-memory process's wavelet coefficients. Using simulated and empirical stock return data, we find that our algorithm produces uncorrelated draws of the posterior distribution and point estimates that rival existing long-memory stochastic volatility estimators.