Robust estimators of accelerated failure time regression with generalized log-gamma errors

TL;DR

This paper introduces robust and efficient estimators for the generalized log-gamma distribution and accelerated failure time models with censored data, validated through simulations and real data applications.

Contribution

It proposes new estimators that are both highly robust and efficient for GLG parameters and AFT models with censored observations, with proven asymptotic properties.

Findings

Estimators are asymptotically fully efficient.

Simulations show high robustness and efficiency.

Real data examples demonstrate good estimator behavior.

Abstract

The generalized log-gamma (GLG) model is a very flexible family of distributions to analyze datasets in many different areas of science and technology. In this paper, we propose estimators which are simultaneously highly robust and highly efficient for the parameters of a GLG distribution in the presence of censoring. We also introduced estimators with the same properties for accelerated failure time models with censored observations and error distribution belonging to the GLG family. We prove that the proposed estimators are asymptotically fully efficient and examine the maximum mean square error using Monte Carlo simulations. The simulations confirm that the proposed estimators are highly robust and highly efficient for finite sample size. Finally, we illustrate the good behavior of the proposed estimators with two real datasets.