论文信息 - The Independence Assumption for a Series or Parallel System When Component Lifetimes Are Exponential

The Independence Assumption for a Series or Parallel System When Component Lifetimes Are Exponential

A common assumption made In modeling system life from series and parallel systems is that the component lives are independent. This study investigates the magnitude of the errors one may incur by erroneously asuming the component lifetimes have independent exponential distributions when in fact the lifetimes follow the bivariate exponential distribution of Marshall & Olkin (series or parallel systems) or that of Freund (parallel systems).

John P. Klein | M. L. Moeschberger | J. Klein | M. Moeschberger

[1] W. R. Buckland. Theory of Competing Risks , 1978 .

[2] Anne Chao,et al. Approximate Mean Squared Errors of Estimators of Reliability for k-out-of-m Systems in the Independent Exponential Case , 1981 .

[3] M. Sobel,et al. Some Theorems Relevant to Life Testing from an Exponential Distribution , 1954 .

[4] I. Olkin,et al. A Multivariate Exponential Distribution , 1967 .

[5] Nancy R. Mann. Simplified Expressions for Obtaining Approximately Optimum System-Reliability Confidence Bounds from Exponential Subsystem Data , 1974 .

[6] John P. Klein,et al. Some recent results in competing risks theory , 1982 .

[7] J. E. Freund. A Bivariate Extension of the Exponential Distribution , 1961 .

[8] T. Boardman,et al. Estimation In Compound Exponential Failure Models , 1970 .