Accelerated Failure Time Models with Logconcave Errors

50 Pages Posted: 17 Jul 2019

See all articles by Ruixuan Liu

Ruixuan Liu

Emory University - Department of Economics

Zhengfei Yu

University of Tsukuba

Date Written: March 1, 2019

Abstract

We study accelerated failure time models in which the survivor function of the error term is log-concave. The log-concavity assumption is often implied by the underlying economic models and covers large families of commonly used distributions. For right-censored failure time data, we construct semi-parametric maximum likelihood estimates of the finite dimensional parameter subject to the shape restriction and establish the large sample properties. The shape restriction also facilitates computation, as the optimization problem has a unique global solution with probability tending to one. Simulation studies and empirical applications demonstrate the usefulness of our method.

Keywords: AFT Models, NPMLE, Weighted Rank Estimation, Shape Restriction, Semiparametric Efficiency

JEL Classification: C14, C24, C41

Suggested Citation

Liu, Ruixuan and Yu, Zhengfei, Accelerated Failure Time Models with Logconcave Errors (March 1, 2019). Available at SSRN: https://ssrn.com/abstract=3420931 or http://dx.doi.org/10.2139/ssrn.3420931

Ruixuan Liu (Contact Author)

Emory University - Department of Economics ( email )

1602 Fishburne Drive
Atlanta, GA 30322
United States

Zhengfei Yu

University of Tsukuba ( email )

Tsukuba University , Ibaraki Ken
Tsukuba, Ibaraki 305-8573, Ibaraki 3050006
Japan

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
11
Abstract Views
129
PlumX Metrics