|
Activity Number:
|
69
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #306849 |
|
Title:
|
Predictive Discrepancy Using Full Cross-Validation for Regression Models
|
|
Author(s):
|
Mark Greenwood*+
|
|
Companies:
|
Montana State University
|
|
Address:
|
Department of Mathematical Sciences, Bozeman, MT, 59717-2400,
|
|
Keywords:
|
model selection ; cross validation ; linear regression
|
|
Abstract:
|
Full cross-validation (FCV) based estimates of the Mean Squared Error of Prediction (MSEP) have been recommended as potential model selection criteria (Bunke, Droge and Polzehl, 1999). They have shown FCV can be used to find better estimates of MSEP than typical cross-validation (CV) and suggest its use in model selection criteria. Neath, Davies and Cavanaugh (2004) suggest a model selection criterion based on cross-validation called the Predictive Discrepancy Criterion (PDC) which is an estimate of the Kullback-Leibler discrepancy. It provides improved performance over typical CV-based criteria and the AIC. The development of a FCV-based analogue of the PDC is described. All the different criteria are then compared using simulations. Extensions to nonlinear regression model selection are also discussed.
|
- 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 2006 program |
