A note on life testing under competing causes of failure with Type I censoring

• Main Authors: Low, Chan Kee, Balasooriya, Uditha
• Other Authors: Nanyang Business School
• Format: Research Report
• Published: 2008
• Subjects: DRNTU::Business::Management
• Online Access: http://hdl.handle.net/10356/7042
• Institution: Nanyang Technological University

In this note we further discuss Type I progressively censored variable-sampling plans for Weibull/extreme value lifetime distributions under competing causes of failure. In the computations of sampling plans for life test experiments where specimens are subject to competing causes of failure, Balasooriya and Low [1] used one of the failure distributions to approximate the exact failure distribu-tion. This approximation is in fact unnecessary as one can use numerical meth-ods to compute the quantiles of the exact failure distribution. Since the revised sampling plan can differ significantly from that based on the approximate failure distribution, it is recommended that the exact failure distribution be used as far as possible, when there are two or more failure modes. Reliability, Type I Progressive censoring, Competing causes of failure, Acceptance sampling, Weibull distribution, Extreme-value distribution.