American Statistical Association
New York City
Metropolitan Area Chapter

Mailman School of Public Health
Columbia University
Department of Biostatistics Colloquium



COMPOSITE LIKELIHOOD EM ALGORITHM AND APPLICATIONS

by

Dr. Peter Song
Department of Statistics and Actuarial Science
University of Waterloo, Canada


Abstract

The method of composite likelihood provides an estimation procedure useful in high-dimensional parametric models that involve complicated dependency or hierarchical structures. In such cases, the full likelihood approach is often computationally intractable. This talk will focus on an extension of the EM algorithm in the framework of composite likelihood estimation in the presence of missing data or latent variables. Several properties of the proposed algorithm will be discussed. Both analytic and empirical performances of the proposed algorithm are illustrated through simulation studies and real world data examples. In particular, a comparison of the new algorithm to the full likelihood EM algorithm and its application in the gene network construction will be presented in detail.


Date: Thursday, September 25, 2008
Time: 4:00 - 5:00 P.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
Judith Jansen Conference Room
4th Floor - Room 425
New York, New York

RESERVATIONS ARE NOT REQUIRED

Refreshments will be served at 3:30 P.M. in the
Biostatistics Conference Room (R627).


Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites
NYC ASA Chapter Constitution | NYC ASA Chapter By-Laws

Copyright © 2008 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to nycasa@mindspring.com