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

TitreRobust estimators of accelerated failure time regression with generalized log-gamma errors
Publication TypeJournal Article
Year of Publication2017
AuthorsAgostinelli, C, Locatelli, I, Marazzi, A, Yohai, íctorJ
JournalComputational Statistics & Data Analysis
Volume107
Pagination92 - 106
Date Published03/2017
DOI10.1016/j.csda.2016.10.012
ISSN0167-9473
Mots-clésCensored data, Quantile distance estimatesτ estimators, Truncated maximum likelihood estimators, Weighted likelihood estimators
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. Estimators are proposed which 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.

WOS ID (UT)

000391774200007

Short TitleComputational Statistics & Data Analysis
Citation Key / SERVAL ID8074
Peer reviewRefereed

                         

IUMSP | www.iumsp.ch
Institut universitaire de médecine sociale et préventive
Route de la Corniche 10, 1010 Lausanne - Switzerland
+41 21 314 72 72 | dess.info@unisante.ch

Go to top