成败型产品基于验后概率的Bayes序贯检验技术

刘琦; 王囡; 唐旻

成败型产品基于验后概率的Bayes序贯检验技术

国防科学技术大学信息系统与管理学院,长沙 410073

基金项目: 国家自然科学基金(70971133)

计量
- 文章访问数: 1819
- HTML浏览量: 103
- PDF量: 1197
- 被引次数: 0
出版历程
- 收稿日期: 2012-04-16
- 刊出日期: 2013-03-28

Bayes sequential test technique for binomial product based on posterior probability

College of Information System and Management, National University of Defense Technology, Changsha 410073, China

摘要

摘要: 分析了基于损失的Bayes检验方法和基于风险的SPOT(sequential posterior odd test)方法存在的不足.对装备试验与评价中成败型产品的Bayes序贯检验,在给定的两类风险要求下,建立了基于验后概率的Bayes序贯检验模型(PBSTM),给出了模型的求解算法和实际验后风险的计算公式. 最后结合装备可靠性分析案例,进行了示例分析,从数据上证明了PBSTM模型优越性和有效性.研究结果表明:PBSTM模型从理论上保证了序贯检验的结论同时满足小概率事件原理和两类风险要求,避免了现有假设检验方法存在的不足.
- Bayes方法 /
- 验后概率 /
- Bayes序贯检验 /
- 验后风险 /
- 成败型产品
Abstract: Defects of Bayes hypothesis test method based on posterior loss and sequential posterior odd test (SPOT) method based on risks were analyzed. According to the requirement of binomial product's Bayes sequential test in equipment test and evaluation, considering the constraints of producer's risk and consumer's risk, posterior probability based sequential test model (PBSTM) was constructed, the PBSTM solving algorithm and formulas of actual posterior risks were presented. At last, with an example in equipment reliability analysis, the superiority and effectiveness of PBSTM was proved by data.The result shows :PBSTM guaranteed in theory that the results of sequential test can satisfy the small probability event principle and risks requirement simultaneously, and avoid the defects of existing methods.
- Bayes method /
- posterior probability /
- Bayes sequential test /
- posterior risk /
- binomial product

HTML

参考文献(16)

[1]	Lenard T,Hsu J S J.Bayesian methods[M].Beijing:China Machine Press,2006.
[2]	Berger J O,Brown L D,Wolpert R L.A unified conditional frequentist and Bayesian test for fixed and sequential simple hypothesis-testing[J].The Annals of Statistics,1994,22(4):1787-1807.
[3]	张金槐,刘琦,冯静.Bayesian试验分析方法[M].长沙:国防科技大学出版社,2007.
[4]	Ganesan R,Rao A N V,Das T K.A multiscale Bayesian SPRT approach for online process monitoring[J].IEEE Transactions on Semiconductor Manufacturing,2008,21(3):399-412.
[5]	Kulacsy K.Further comments on the sequential probability ratio testing methods[J].Annals of Nuclear Energy,1997,24(13):1005-1012.
[6]	GUO Bo,JIANG Ping,XING Yunyan.A censored sequential posterior odd test (SPOT) method for verification of the mean time to repair[J].IEEE Transactions on Reliability,2008,57(2):243-247.
[7]	Peskir G,Shiryaev A N.Sequential testing problems for Poisson processes[J].The Annals of Statistics,2000,28(3):859.
[8]	刘琦,王囡.基于验后概率的Bayesian序贯方差检验技术(Ⅰ)[J].航空动力学报,2011,26(7):1531-1536. LIU Qi,WANG Nan.Bayesian sequential variance test technique based on posterior probability: PartⅠ[J].Journal of Aerospace Power,2011,26(7):1531-1536.(in Chinese)
[9]	刘琦,王囡.基于验后概率的Bayesian序贯方差检验技术(Ⅱ)[J].航空动力学报,2011,26(7):1537-1542. LIU Qi,WANG Nan.Bayesian sequential variance test technique based on posterior probability: Part Ⅱ[J].Journal of Aerospace Power,2011,26(7):1537-1542.(in Chinese)
[10]	张金槐.正态总体下分布参数的Bayesian序贯估计[J].国防科技大学学报,2002,24(2):95-100. ZHANG Jinhuai.Bayesian sequential estimation of the parameter for normal sample[J].Journal of National University of Defense Technology,2002,24(2):95-100.(in Chinese)
[11]	XING Yunyan,WU Xiaoyue.Bayesian sequential testing for exponential life system with reliability growth[J].Journal of Systems Engineering and Electronics,2011,22(6):1023-1029.
[12]	LIU Qi,AN Min.A posterior probability based sequential binomial test method for verification of success ratio p[J].World Journal of Engineering,2011,8(4):313-325.
[13]	Li X R, Li X B.Common fallacies in applying hypothesis testing[R].New York:Proceedings of the 11th International Conference on Information Fusion,2008.
[14]	武小悦,刘琦.装备试验与评价[M].北京:国防工业出版社,2008.
[15]	Berger J O.Statistical decision theory and Bayesian analysis[M].New York:Springer-Verlag,1998.
[16]	Hamada M S,Wilson A G,Reese C S,et al.Bayesian Reliability[M].New York:Physical and Information Science,2008.