广义逐步混合删失方案下广义指数分布的参数推断

基金项目: 国家自然科学基金项目(批准号: 11501167)和河南省高等学校重点科研项目(批准号: 15A110025)资助.

详细信息

Parameters Inference of Generalized Exponential Distribution Based on Generalized Progressively Hybrid Censoring Scheme

School of Statistics and Mathematics, Central University of Finance and Economics
School of Mathematics and Statistics, Henan University of Science and Technology
School of Mathematics and Information Science, Longnan Teacher College

摘要: 广义逐步混合删失方案作为一种新的可靠性试验方案, 它可以保证试验结束前得到一定数量的失效样本以提高试验效率. 基于寿命数据分析中广泛使用的广义指数分布, 本文考虑了其在广义逐步混合删失方案下的参数推断问题. EM算法被用来给出模型的参数估计. 模拟研究和一组实际数据分析展示了所提方法的有限样本表现.
- 广义指数分布 /
- 失效样本 /
- 广义逐步混合删失 /
- EM算法
Abstract: As a new reliability test plan, generalized progressive hybrid censoring can improve test efficiency by allowing experimenters to observe a pre-specified number of failure samples before the final termination point. Based on a class of widely used life distribution in life data analysis ---generalized exponential distribution, this paper discusses its parameters inference issue under generalized progressive hybrid censoring scheme. EM Algorithm is used to estimate parameters of the considered model. Simulation studies and a real-data analysis are carried out to illustrate the performance of finite sample for the proposed procedure.
- generalized exponential distribution /
- failure samples /
- generalized progressive hybrid censoring /
- EM algorithm