Dear all,
There has been a change in the title and abstract of Simon Godsill's
talk. Details are given below. Apologies for the change at this late
change.
Institute of Mathematics and Statistics,
University of Kent at Canterbury,
Statistics Seminar -- Trinity Term 1999
Thursday, 1st July 1999
2:00pm Dr Simon Godsill
(Cambridge University)
Title: Bayesian inference for time series with heavy-tailed
symmetric $\alpha$-stable noise processes
Abstract:
In this paper we present both stochastic and deterministic iterative
methods for inference about random processes with symmetric stable
innovations. The proposed methods use a scale mixtures of normals (SMiN)
representation of the symmetric stable law to express the processes in
conditionally Gaussian form. This allows standard procedures for dealing
with the Gaussian case to be re-used directly as part of the scheme. In
contrast with other recently
published work on the topic, we propose a novel hybrid rejection sampling
method for simulating the scale parameters from their full conditional
distributions, making use of asymptotic approximations for the tail of a
positive stable distribution when rejection rates are too high. This
hybrid
approach leads to improved performance compared with straightforward
rejection sampling or Metropolis-Hastings (M-H) approaches. The methods
can be applied to any model with symmetric stable terms, but we
illustrate their
application to linear models and present simulations for AR time series
with symmetric stable innovations.
****************
Further details of the seminar programme and abstracts of
forthcoming talks are available from:
http://www.ukc.ac.uk/IMS/statistics/people/T.Sapatinas/Seminars/
seminars.html
All are very welcome. The Statistics Seminars will be held in
Mathematics Lecture Theatre in the Institute of Mathematics and
Statistics, Cornwallis Building.
The following WWW page contain details of how to get to the campus,
and how to find your way around:
http://www.ukc.ac.uk/ukc/location.html
================================================================
Dr Theofanis Sapatinas,
Lecturer in Statistics,
Postal Address: Institute of Mathematics and Statistics,
University of Kent at Canterbury,
Canterbury, Kent CT2 7NF,
United Kingdom.
Tel: ++(44)-1227-827253
Fax: ++(44)-1227-827932
Email: [log in to unmask]
URL: http://www.ukc.ac.uk/IMS/statistics/people/T.Sapatinas/
================================================================
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|