|
Activity Number:
|
274
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #306801 |
|
Title:
|
Efficient Computation and Variable Selection for the L1-Norm Quantile Regression
|
|
Author(s):
|
Youjuan Li*+ and Ji Zhu
|
|
Companies:
|
University of Michigan and University of Michigan
|
|
Address:
|
1737 Cram Circle, Ann Arbor, MI, 48015,
|
|
Keywords:
|
degrees of freedom ; L1-norm ; quantile regression ; variable selection
|
|
Abstract:
|
Classical regression methods have focused on mainly estimating conditional mean functions. However, in recent years, quantile regression has emerged as a comprehensive approach to the statistical analysis of response models. We consider the L1-norm regularized quantile regression (L1-norm QR), which uses the sum of the absolute values of the coefficients as the penalty. The L1-norm penalty has the advantage of simultaneously controlling the variance of the fitted coefficients and performing automatic variable selection. We propose an efficient algorithm that computes the entire solution path of the L1-norm QR. We also derive an unbiased estimate for the degrees of freedom of the L1-norm QR model, which allows convenient selection of the regularization parameter.
|
