This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 382
Type: Invited
Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Mining
Abstract - #306253
Title: Stability and Inference Model Selection
Author(s): Leonard A. Stefanski*+
Companies: North Carolina State University
Address: Department of Statistics, Raleigh, NC, 27511,
Keywords: Bootstrap ; Jackknife ; Resampling ; Variable Selection ; Bagging ; Model Averaging
Abstract:

Model averaging improves prediction, but it complicates parameter inference because of the complex dependence of the averaged coefficient estimator on the data. Resampling methods are attractive here. However, excessive computation is an issue as model averaging itself is usually computationally time consuming. This talk will describe three approaches to variance estimation after bagging: Efron's jackknife after bootstrap, the double bootstrap, and a third, new approach herein called the parallel bootstrap. Although model averaging is often beneficial for prediction, it is not always. Thus, because the improvement in prediction is often achieved at the expense of interpretability, it is important to know when model averaging is advantageous and when it is not. The talk will also describe a model-stability index that is applicable to general regression models.


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 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.