|
Activity Number:
|
258
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Society of Bayesian Analysis
|
| Abstract - #307789 |
|
Title:
|
Bayesian Semiparametric Factor Modeling in Large P Problems
|
|
Author(s):
|
Mike West*+
|
|
Companies:
|
Duke University
|
|
Address:
|
Box 90251, Durham, NC, 27708-0251,
|
|
Keywords:
|
Bayesian factor models ; Dirichlet process priors ; Gene expression analysis ; Biological pathway ; Cancer genomics
|
|
Abstract:
|
Large-scale Bayesian latent factor models are now central tools in a range of our studies of complex, interconnected substructure in gene pathway biology. This talk will overview some of the models and methodology, and highlight the integration of non-parametric model components that very naturally reflect what can be highly non-Gaussian distributions in factor space. Examples drawn from cancer pathway studies will highlight the methodology.
|
