JSM 2005 Online Program

Abstract #302505

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2005); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page

Legend:

= Applied Session,

= Theme Session,

= Presenter

Activity Number:	344
Type:	Invited
Date/Time:	Wednesday, August 10, 2005 : 8:30 AM to 10:20 AM
Sponsor:	Section on Statistical Computing
Abstract - #302505
Title:	Maximum Likelihood Parameter Estimation in General State-Space Models Using Particle Methods
Author(s):	Sumeetpal S. Singh*+ and George Poyiadjis and Arnaud Doucet
Companies:	Cambridge University and Cambridge University and Cambridge University
Address:	Trumpington Street, Engineering Department, Cambridge, International, CB2 1PZ, United Kingdom
Keywords:	particle filter ; parameter estimation ; general state-space ; filter derivative ; hahn-jordan decomposition
Abstract:	Many time-series models in applied statistics, engineering, etc., can be described by the class of nonlinear, nonGaussian state-space models. While state estimation for these models is now routinely performed using the particle filter, maximum likelihood parameter estimation is much more challenging. In this paper, we present new numerical methods to perform batch and recursive maximum likelihood parameter estimation and tracking---we develop a gradient ascent method to maximize the likelihood. This requires maintaining a particle approximation of the derivative of the optimal filter, which is a signed measure. We also study the jump Markov linear model in detail and describe how significant computation savings may be obtained using the Rao-Blackwell approach.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2005 program