Pitt, Michael K. and Walker, S. G. (Stephen G.) (2001) Construction of stationary time series via the Gibbs sampler with application to volatility models. Working Paper. Coventry: University of Warwick, Department of Economics. Warwick economic research papers (No.595).

Preview

PDF WRAP_Pitt_twerp595.pdf - Requires a PDF viewer. Download (422Kb)

Request Changes to record.

Abstract

In this paper, we provide a method for modelling stationary time series. We allow the family of marginal densities for the observations to be specified. Our approach is to construct the model with a specified marginal family and build the dependence structure around it. We show that the resulting time series is linear with a simple autocorrelation structure. In particular, we present an original application of the Gibbs sampler. We illustrate our approach by fitting a model to time series count data with a marginal Poisson-gamma density.

Item Type:	Working or Discussion Paper (Working Paper)
Subjects:	H Social Sciences > HB Economic Theory Q Science > QA Mathematics
Divisions:	Faculty of Social Sciences > Economics
Library of Congress Subject Headings (LCSH):	Markov processes, Monte Carlo method, Probabilities, Stochastic processes
Series Name:	Warwick economic research papers
Publisher:	University of Warwick, Department of Economics
Place of Publication:	Coventry
Official Date:	2001
Dates:	Date Event 2001 Published
Number:	No.595
Number of Pages:	31
Status:	Not Peer Reviewed
Access rights to Published version:	Open Access (Creative Commons)

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads