Start-Up Demonstration Tests Based on Consecutive Successes and Total Failures
Start-Up Demonstration Tests Based on Consecutive Successes and Total Failures
复制标题
DOI：
10.1080/00224065.2005.11980320
复制
发表时间：
2005-07
影响因子：
2.5
通讯作者：
Michelle L. Depoy Smith;W. Griffith
中科院分区：
文献类型：
--
作者：
Michelle L. Depoy Smith;W. Griffith
启动演示测试需要在 f 次失败之前连续成功接受 k 次，否则将被拒绝。给出了通用的马尔可夫链方法，允许用户轻松计算期望、方差、概率质量函数、测试长度的分布以及设备被接受的概率等量。这种方法产生了紧凑的公式，很容易被实践者实现和理解，并自然地扩展到非独立同分布。案件。推导的程序为确定适当的启动演示测试参数 k 和 f 提供指导。计算并研究基于最大似然估计的 p 置信度陈述，即启动演示测试的可靠性。
The start-up demonstration test that requires k consecutive successes for acceptance prior to f total failures and rejection otherwise is examined. A general Markov Chain approach is given that allows the user to easily calculate quantities such as expectation, variance, probability mass function, and the distribution of the test length, as well as the probability the equipment will be accepted. This methodology produces compact formulas that are readily implemented and understood by the practitioner and naturally extend to the non-i.i.d. case. Procedures are derived to give guidance for determining the appropriate startup demonstration test parameters k and f. Confidence statements for p, the reliability for the start-up demonstration test, based on maximum likelihood estimators, are calculated and investigated.