BOOTSTRAPPING INTERVAL ESTIMATION OF SOFTWARE RELIABILITY BASED ON DISCRETIZED NHPP MODEL

摘要：

　　Software reliability assessment based on Software Reliability Growth Models (abbreviated as SRGMs) is mostly conducted by point estimation of model parameters and reliability assessment measures.However, most of software fault data are incomplete.In addition, it is difficult to obtain sufficient reliability data in an actual testing-phase.Therefore, it is better to estimate these measures based on the interval estimation.That is, it is important to consider the uncertainly of the parameter estimations in the reliability assessment measures.However, because the interval estimation which is needed to be considered the uncertainly is difficult to mathematically analyze.In this study, we discuss bootstrap method for the interval estimation of the parameters and the reliability assessment measures based on the discrete inflection S-shaped SRGM.The bootstrap method is the typical method of statistical calculation method.Finally, we show numerical examples of our approach by using actual data.

关键词： Software reliability assessment Bootstrap method Software reliability growth model Interval estimation Discretized NHPP model Reliability assessment measure

作者: Shintaro Okada Shinji Inoue Shigeru Yamada

作者单位: Department of Social Management Engineering, Graduate School of Engineering, Tottori University, Tottori 680-8552, Japan

会议类型: 国际会议

会议名称: The 12th International Conference on Industrial Management(第十二届工业管理国际会议)

会议地点: 成都

会议语种:英文

页码: 255-259

在线出版日期: 2014-09-03（万方平台首次上网日期，不代表论文的发表时间）