dc.contributor.advisor Mukerjee, Hari en_US dc.contributor.author Malla, Ganesh B. en_US dc.date.accessioned 2010-09-01T16:09:37Z dc.date.available 2010-09-01T16:09:37Z dc.date.issued 2009-07 en_US dc.identifier.other d09022 en_US dc.identifier.uri http://hdl.handle.net/10057/2547 dc.description Thesis (Ph.D.)--Wichita State University, College of Liberal Arts and Sciences, Dept. of Mathematics and Statistics en_US dc.description.abstract In survival analysis and in the analysis of the life tables an important biometric function of interest is the mean residual life function (MRLF) M whose value at age t is en_US the average future life time given that a subject has survived till time t. Two important classes of the MRLFs are the New Better than Used in Expectation (NBUE) class' and Decreasing Mean Residual Life (DMRL) class'. These two classes are defined as {M(t):M(t)≤M(0), t≥0} and {M(t):M(t)≤M(s), if t≥s} respectively. In this dissertation we consider the problem of estimation and testing for the distributions in the NBUE and DMRL classes under random censoring. Our order restricted estimators of M for the NBUE and DMRL classes are respectively M*n(t) = Mn(t)٨Mn(0) and Mn**(t) = infy≤t Mn(y), where Mn is the Kaplan-Meier estimator of M. We have proven that both these estimators are uniformly strongly consistent, and converge weakly to a Gaussian process. By simulation, we have also shown that our estimators are better than Mn in terms of asymptotic mean sums of squares. Several applications of our estimators have been provided. Tests that identify the NBUE or DMRL behavior have been developed. Both tests are shown to be consistent in their classes. We have derived the asymptotic distributions of our test statistics. dc.format.extent xii, 79 p. en_US dc.format.extent 320485 bytes dc.format.mimetype application/pdf dc.language.iso en_US en_US dc.publisher Wichita State University en_US dc.subject.lcsh Electronic dissertations en dc.title Order restricted inferences about lifetimes under censoring en_US dc.type Dissertation en_US
﻿