|
Activity Number:
|
1
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #310171 |
|
Title:
|
Local Graphical Model Search
|
|
Author(s):
|
Liang Zhang*+ and Adrian Dobra and Mike West
|
|
Companies:
|
Duke University and University of Washington and Duke University
|
|
Address:
|
214 Old Chem, Durham, NC, 27708,
|
|
Keywords:
|
Local Graphical Model Search ; MCMC ; Metropolis-Hastings
|
|
Abstract:
|
Compared to general graphical model search methods, we present here our work on local graphical model search algorithms. Local graphical model search algorithms will apply to the problem if we are only interested in one gene Y in thousands of genes in the gene expression data, for example, and wish to understand the graphical structure of Y and its graphical structure, where usual (global) graphical model search methods will not be efficient and precise. Also, the prediction of Y based on the local graphical structure is one of our interests. Monte Carlo Markov Chain methods and Shotgun Stochastic Search will be tried to do the search. We will provide several examples to analyze the efficiency as well as the precision of our algorithms.
|
