LAD-Lasso variable selection for doubly censored median regression models

ABSTRACT

A variable selection procedure based on least absolute deviation (LAD) estimation and adaptive lasso (LAD-Lasso for short) is proposed for median regression models with doubly censored data. The proposed procedure can select significant variables and estimate the parameters simultaneously, and the resulting estimators enjoy the oracle property. Simulation results show that the proposed method works well.

Keywords:

• Doubly censored data
• LAD-Lasso
• Median regression model
• Oracle property.

MATHEMATICS SUBJECT CLASSIFICATION:

• 62N02
• 62J07

Funding

The research is supported by NSFC (No. 11201235) and Program of Natural Science Research of Jiangsu Higher Education Institutions of China (No. 12KJB110010).