A new particle filtering approach to estimate stochastic volatility models with Markov-switching

Frédéric Karamé

Post-Print from HAL

Abstract: A simple method is proposed to estimate stochastic volatility models with Markov-switching. It relies on a nested structure of filters (a Hamilton filter and several particle filters) to approximate unobserved regimes and state variables, respectively. Smooth resampling is used to keep the computational complexity constant over time and to implement a standard likelihood-based inference on parameters. A bootstrap and an adapted version of the filter are described and their performance are assessed using simulation experiments. The volatility of US and French markets is characterized over the last decade using a three-regime stochastic volatility model extended to include a leverage effect.

Keywords: Stochastic volatility; Bayesian inference; Markov switching; Particle filtering; Smooth resampling; Kim filter; nonlinear Kalman filter (search for similar items in EconPapers)
Date: 2018-10
References: Add references at CitEc
Citations:

Published in Econometrics and Statistics , 2018, 8, pp.204-230. ⟨10.1016/j.ecosta.2018.05.004⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
Journal Article: A new particle filtering approach to estimate stochastic volatility models with Markov-switching (2018)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-02296093

DOI: 10.1016/j.ecosta.2018.05.004

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().