JSM 2005 Online Program

Abstract #304184

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:	136
Type:	Contributed
Date/Time:	Monday, August 8, 2005 : 10:30 AM to 12:20 PM
Sponsor:	Section on Bayesian Statistical Science
Abstract - #304184
Title:	Estimating Model Complexity for Bayesian Networks
Author(s):	Avraham Salzman*+ and Anthony Almudevar
Companies:	University of Rochester and University of Rochester
Address:	Dept of Biostatistics and Comp Biology, rochester, NY, 14620, United States
Keywords:	bayesian network ; simulated annealing ; MCMC ; model selection
Abstract:	Bayesian networks are used commonly to model complex genetic interaction graphs in which genes are represented by nodes and interactions by directed edges. Although a likelihood function usually is well defined, the maximum likelihood approach favors highly connected networks. To overcome this, we propose a measure of complexity and a two-step algorithm to learn the network structure. First, we estimate model complexity. This requires finding the MLE conditional on model complexity. This is accomplished using simulated annealing to solve a constrained optimization problem on the graph space. In the second step, we use a MCMC algorithm to construct a posterior density of gene graphs that incorporates the information obtained in the first step. Our approach is illustrated by an example and compared to standard model selection methods.

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