© 1997 by Biometrika Trust
Likelihood analysis of non-Gaussian measurement time series
Nuffield College Oxford, OX1 1NF, U.K. e-mail: neil.shephard{at}nuf.ox.ac.uk
Department of Statistics, University of Oxford OX1 3TG, U.K. e-mail: michael.pitt{at}nuf.ox.ac.uk
In this paper we provide methods for estimating non-Gaussian time series models. These techniques rely on Markov chain Monte Carlo to carry out simulation smoothing and Bayesian posterior analysis of parameters, and on importance sampling to estimate the likelihood function for classical inference. The time series structure of the models is used to ensure that our simulation algorithms are efficient.
Key Words: Blocking Exponential family Importance sampling Markov chain Monte Carlo Simulation smoother Stochastic volatility
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
B. Jungbacker and S. J. Koopman Monte Carlo Estimation for Nonlinear Non-Gaussian State Space Models Biometrika, December 1, 2007; 94(4): 827 - 839. [Abstract] [PDF] |
||||
![]() |
M. Beine, C. S. Bos, and S. Laurent The Impact of Central Bank FX Interventions on Currency Components J. Financial Econometrics, January 1, 2007; 5(1): 154 - 183. [Abstract] [Full Text] [PDF] |
||||
![]() |
E. L. Ionides, C. Breto, and A. A. King Inference for nonlinear dynamical systems PNAS, December 5, 2006; 103(49): 18438 - 18443. [Abstract] [Full Text] [PDF] |
||||
![]() |
D. Feng, G. J. Jiang, and P. X.-K. Song Stochastic Conditional Duration Models with "Leverage Effect" for Financial Transaction Data J. Financial Econometrics, June 1, 2004; 2(3): 390 - 421. [Abstract] [Full Text] [PDF] |
||||


