Online Program Home
My Program

Abstract Details

Activity Number: 466 - First-Hitting-Time Based Threshold Regression and Applications
Type: Topic Contributed
Date/Time: Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
Sponsor: Section on Risk Analysis
Abstract #328920
Title: Censored Threshold Regression with Diverging Number of Covariates
Author(s): Takumi Saegusa* and Mei-Ling Ting Lee
Companies: University of Maryland and University of Maryland
Keywords: survival; threshold regression; variable selection

We develop a new sparse threshold regression method for high-dimensional survival data with right censoring. Our method is an iteratively reweighted penalized threshold regression where the number of covariates diverges as a sample size goes to infinity. We establish its oracle property for variable selection and estimation errors, a grouping property for highly correlated covariates, and asymptotic normality of the proposed estimator. The performance of our method is illustrated using simulations and real data examples.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program