location: Current position: Home >> Scientific Research >> Paper Publications

Penalized Empirical Likelihood via Bridge Estimator in Cox's Proportional Hazard Model

Hits:

Indexed by:期刊论文

Date of Publication:2014-01-17

Journal:COMMUNICATIONS IN STATISTICS-THEORY AND METHODS

Included Journals:SCIE、EI

Volume:43

Issue:2

Page Number:426-440

ISSN No.:0361-0926

Key Words:Bridge estimator; Cox's proportional hazard model; Empirical likelihood; Variable selection; 62G05; 62N01

Abstract:We propose the penalized empirical likelihood method via bridge estimator in Cox's proportional hazard model for parameter estimation and variable selection. Under reasonable conditions, we show that penalized empirical likelihood in Cox's proportional hazard model has oracle property. A penalized empirical likelihood ratio for the vector of regression coefficients is defined and its limiting distribution is a chi-square distributions. The advantage of penalized empirical likelihood as a nonparametric likelihood approach is illustrated in testing hypothesis and constructing confidence sets. The method is illustrated by extensive simulation studies and a real example.

Pre One:A note on the one-step estimator for ultrahigh dimensionality

Next One:Profile Likelihood Inferences on the Partially Linear Model with a Diverging Number of Parameters