|
Activity Number:
|
595
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #304954 |
|
Title:
|
Bootstrapping Lasso Estimators
|
|
Author(s):
|
Arindam Chatterjee*+
|
|
Companies:
|
Texas A&M University
|
|
Address:
|
Dept. of Statistics, 3143 TAMU, College Station, TX, 77843-3143,
|
|
Keywords:
|
Bootstrap ; Penalized regression ; Shrinkage ; Variance estimation
|
|
Abstract:
|
In this paper, we consider bootstrapping the Lasso estimator of the regression parameter in a multiple linear regression model. It is shown that the usual residual based bootstrap fails to be consistent. We derive the asymptotic distribution of the bootstrapped Lasso estimator, which clearly reveals the main reason for its failure. We also propose a modified bootstrap method, and establish its validity for approximating the distribution of the Lasso estimator. We also establish consistency of the modified bootstrap method for estimating the asymptotic bias and variance of the Lasso estimator.
|
- 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 2009 program |
