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

Charles S. Bos, Neil Shephard

Research output: Working paperProfessional

65 Downloads (Pure)

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.
Original languageEnglish
Place of PublicationAmsterdam
PublisherTinbergen Instituut
Publication statusPublished - 2004

Publication series

NameDiscussion paper TI
No.04-015/4

Fingerprint Dive into the research topics of 'Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space form'. Together they form a unique fingerprint.

  • Cite this

    Bos, C. S., & Shephard, N. (2004). Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space form. (Discussion paper TI; No. 04-015/4). Amsterdam: Tinbergen Instituut.