Journal of Statistics: Advances in Theory and ApplicationsAuthor's: Qiqing Yu
Pages: [83] - [108]
Received Date: June 07, 2021
Submitted by:
DOI: http://dx.doi.org/10.18642/jsata_7100122213
Under the right censorship model and under the linear regression model
where 
may not exist, the modified semi-parametric MLE
(MSMLE) was proposed by Yu and Wong [17]. The MSMLE 
of 
satisfying 
infinitely often) 
if 
is discontinuous, and the simulation study
suggests that it is also consistent and efficient under certain
regularity conditions. In this paper, we establish the consistency of
the MSMLE under the necessary and sufficient condition that is identifiable. Notice that under the latter
assumption, the Buckley-James estimator and the median regression
estimator can be inconsistent (see Yu and Dong [20]).
linear regression model, modified semi-parametric maximum likelihood estimator, consistency, right-censored data.
