Quotation Kastner, Gregor, Frühwirth-Schnatter, Sylvia. 2011. Ancillarity-Sufficiency Interweaving Strategy (ASIS) for Boosting MCMC Estimation of Stochastic Volatility Models. 5th CSDA International Conference on Computational and Financial Econometrics (CFE'11), Senate House, University of London, Großbritannien, 17.12.-19.12.


RIS


BibTeX

Abstract

Recent findings show that Bayesian inference for stochastic volatility (SV) models using MCMC methods highly depends on actual parameter values in terms of sampling efficiency. While draws from the posterior utilizing the standard centered parameterization break down when the volatility of volatility parameter in the latent state equation is small, non-centered versions of the model show deficiencies for highly persistent latent variable series. The novel approach of ancillarity-sufficiency interweaving has recently been shown to aid in overcoming these issues for a broad class of multilevel models. In this talk we demonstrate how such an interweaving strategy can be applied to stochastic volatility models in order to greatly improve sampling efficiency for all parameters and throughout the entire parameter range. Moreover, this method of "combining best of different worlds" allows inference for parameter constellations that have previously been unfeasible to estimate without the need to select a particular parameterization beforehand.

Tags

Press 'enter' for creating the tag

Publication's profile

Status of publication Published
Affiliation WU
Type of publication Paper presented at an academic conference or symposium
Language English
Title Ancillarity-Sufficiency Interweaving Strategy (ASIS) for Boosting MCMC Estimation of Stochastic Volatility Models
Event 5th CSDA International Conference on Computational and Financial Econometrics (CFE'11)
Year 2011
Date 17.12.-19.12
Country United Kingdom
Location Senate House, University of London
URL http://www.cfe-csda.org/cfe11/

Associations

People
Kastner, Gregor (Details)
Frühwirth-Schnatter, Sylvia (Details)
Organization
Institute for Statistics and Mathematics IN (Details)
Research areas (ÖSTAT Classification 'Statistik Austria')
1105 Computer software (Details)
1162 Statistics (Details)
5323 Econometrics (Details)
5701 Applied statistics (Details)
5707 Time series analysis (Details)
Google Scholar: Search