Likelihood analysis of non-Gaussian measurement time series. (English) Zbl 0888.62095

Biometrika 84, No. 3, 653-667 (1997); correction 91, No. 1, 249-250 (2004).
Summary: 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.
Corrections for §3.1 are given.


62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
65C99 Probabilistic methods, stochastic differential equations
Full Text: DOI Link