Online Program Home
My Program

Abstract Details

Activity Number: 412
Type: Topic Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: SSC
Abstract #319696
Title: Partially Linear Single-Index Regression for Accelerated Failure Time Models
Author(s): Wenqing He* and Grace Yi
Companies: University of Western Ontario and University of Waterloo
Keywords: AFT Model ; Partially Linear ; Single index ; Failure time ; Semi-parametric model
Abstract:

Accelerated Failure Time (AFT) models are very appealing in modeling the relationship between failure times and associated covariates, where covariate effects are usually assumed to appear in a linear form. Such an assumption of covariate effects is, however, quite restrictive for many practical problems. To incorporate flexible nonlinear relationship between covariates and transformed failure times, we propose partially linear single index models to facilitate complex relationship between failure times and covariates. A semi-parametric quasi-likelihood local approach and a weakly parametric global approach are developed to perform inferences. The issue of robustness to model misspecification is carefully explored. The asymptotic properties for the semiparametric method are established and a real example is used to illustrate the usage of the proposed methods. Simulation studies are conducted to assess the performance of the proposed methods for a broad variety of situations, including misspecification of the error distribution, or of the relationship between the response and covariates. This is a joint work with G. Yi in the University of Waterloo.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association