Realized stochastic volatility with leverage and long memory

Shinichiro Shirota, Takayuki Hizu, Yasuhiro Omori

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)


The daily return and the realized volatility are simultaneously modeled in the stochastic volatility model with leverage and long memory. The dependent variable in the stochastic volatility model is the logarithm of the squared return, and its error distribution is approximated by a mixture of normals. In addition, the logarithm of the realized volatility is incorporated into the measurement equation, assuming that the latent log volatility follows an Autoregressive Fractionally Integrated Moving Average (ARFIMA) process to describe its long memory property. The efficient Bayesian estimation method using Markov chain Monte Carlo method (MCMC) was proposed and implemented in the state space representation. Model comparisons are performed based on the marginal likelihood, and the volatility forecasting performances are investigated using S&P500 stock index returns.

Original languageEnglish
Pages (from-to)618-641
Number of pages24
JournalComputational Statistics and Data Analysis
Publication statusPublished - Aug 2014


  • Leverage effect
  • Long memory
  • Markov Chain Monte Carlo
  • Mixture sampler
  • Realized stochastic volatility model
  • Realized volatility
  • State space model

Fingerprint Dive into the research topics of 'Realized stochastic volatility with leverage and long memory'. Together they form a unique fingerprint.

Cite this