Please use this identifier to cite or link to this item:
Title: Component reliability analysis of k-out-of-n systems with censored data
Authors: Chen, Z. 
Keywords: Data completion
k-out-of-n system
Lifetime distribution
Non-parametric inference
Random censoring
Issue Date: 1-Sep-2003
Citation: Chen, Z. (2003-09-01). Component reliability analysis of k-out-of-n systems with censored data. Journal of Statistical Planning and Inference 116 (1) : 305-315. ScholarBank@NUS Repository.
Abstract: It is well-known that k-out-of-n systems are of great use for improving system reliability by introducing component redundancy. In this article, we develop a method for analyzing component reliability as well as system reliability of k-out-of-n systems with independent and identically distributed components based on system lifetime data. We consider both complete and censored data. In the censored case, we distinguish situations where lifetimes are censored with and without observations on the number of failed components. The estimator of the component lifetime distribution with complete data is obtained by an appropriate functional transformation of the empirical distribution of the observed system lifetimes. The estimator is then adapted for the censored case without observation on the number of failed components by using Kaplan-Meier estimators. A data completion procedure is developed for the situation where observations on the number of failed components are available for censored units. The consistency and asymptotic distribution of the estimators are established. Simulation studies on the effect of the data completion procedure are reported. © 2002 Elsevier Science B.V. All rights reserved.
Source Title: Journal of Statistical Planning and Inference
ISSN: 03783758
DOI: 10.1016/S0378-3758(02)00179-9
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Jan 11, 2019


checked on Jan 2, 2019

Page view(s)

checked on Dec 28, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.