|
Activity Number:
|
247
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Council of Chapters
|
| Abstract - #300066 |
|
Title:
|
Sparse Modeling of Conditional Response Distributions with Many Predictors
|
|
Author(s):
|
David Dunson*+
|
|
Companies:
|
Duke University
|
|
Address:
|
Department of Statistical Science, Durham, NC, 27708-0251,
|
|
Keywords:
|
Nonparametric Bayes ; Variable selection ; Density regression ; Shrinkage ; Quantile regression ; Large p, small n
|
|
Abstract:
|
There is an increasingly rich literature on methods for accommodating high-dimensional predictors in regression, either to identify promising subsets of important predictors or for prediction. Such methods almost always focus on a mean regression setting in which the predictors are related to the mean of the response variable, with the residual distribution assumed to be constant or possibly changing according to a parametric model. Our focus is on using nonparametric Bayes methods to flexibly model the conditional response distribution, allowing the different quantiles of the distribution to change differentially with a high-dimensional set of candidate predictors. We propose an approach based on the kernel stick-breaking process, and illustrate the method with epidemiologic applications.
|
- 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 2008 program |
