Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space Form

Tinbergen Institute Discussion Paper No. 04-015/4

32 Pages Posted: 8 Jun 2004

See all articles by Charles S. Bos

Charles S. Bos

VU University Amsterdam

Neil Shephard

Harvard University

Date Written: January 2004

Abstract

In this paper we replace the Gaussian errors in the standard Gaussian, linear state space model with stochastic volatility processes. This is called a GSSF-SV model. We show that conventional MCMC algorithms for this type of model are ineffective, but that this problem can be removed by reparameterising the model. We illustrate our results on an example from financial economics and one from the nonparametric regression model. We also develop an effective particle filter for this model which is useful to assess the fit of the model.

Keywords: Markov chain Monte Carlo, particle filter, cubic spline, state space form, stochastic volatility

JEL Classification: C15, C32, C51, F31

Suggested Citation

Bos, Charles S. and Shephard, Neil, Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space Form (January 2004). Tinbergen Institute Discussion Paper No. 04-015/4. Available at SSRN: https://ssrn.com/abstract=495922 or http://dx.doi.org/10.2139/ssrn.495922

Charles S. Bos (Contact Author)

VU University Amsterdam ( email )

De Boelelaan 1105
1081 HV Amsterdam
Netherlands

HOME PAGE: http://personal.vu.nl/c.s.bos

Neil Shephard

Harvard University ( email )

1875 Cambridge Street
Cambridge, MA 02138
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
120
Abstract Views
965
rank
244,426
PlumX Metrics