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

CLAUDIO AGOSTINELLI; ISABELLA LOCATELLI; ALFIO; VÍCTOR J. YOHAI

COMPUTATIONAL STATISTICS AND DATA ANALYSIS

ELSEVIER SCIENCE BV

Lugar: Amsterdam; Año: 2017 vol. 107 p. 92 - 116

0167-9473

The generalized log-gamma (GLG) model is a very flexible family of distributions to analyzedatasets in many different areas of science and technology. Estimators are proposedwhich are simultaneously highly robust and highly efficient for the parameters of a GLG distribution in the presence of censoring. Estimators with the same properties for accelerated failure time models with censored observations and error distribution belonging to the GLG family are also introduced. It is proven that the proposed estimators are asymptotically fully efficient and the maximum mean square error is examined using Monte Carlo simulations. The simulations confirm that the proposed estimators are highly robust and highly efficient for a finite sample size. Finally, the benefits of the proposed estimators in applications are illustrated with the help of two real datasets.