摘要
主要研究了工业中可靠性指标R=P(Y Metropolis-Hastings和Adaptive Rejection Metropolis Sampling.最后,通过数值模拟和实际数据的分析来对比不同参数估计方法的性能.
In this paper,the problem of estimating the reliability performance R=P(Ym variables from Weibull distribution with the same scale parameters but different shape parameters.The maximum likelihood estimator and the approximate maximum likelihood estimator of R is obtained.Then the correspondent asymptotic distribution is derived and it is used to construct asymptotic confidence interval.The non-parametric bootstrap confidence intervals is also considered in this article.The Bayesian estimation based on different Gibbs techniques:Metropolis-Hastings and Adaptive Rejection Metropolis Sampling is also proposed.Finally,simulation study and real data analysis are presented to illustrate the performance of different estimation methods.
引文
[1]Samuel Kotz,Yan Lumelskii,Marianna Pensky.The Stress-strength Model and its Generalizations-Theory and Applications[M].Singapore:World Scientific,2003.
[2]Awad A M,Azzam M M,Hamdan M A.Some inference results on pr(xmodel[J].Communications in Statistics-Theory and Methods,1981,10(24):2515-2525.
[3]Gupta R D,Gupta R C.Estimation of p[a x>b y]in the mnltiyariate normal case[J].Statistics,1990,21(1):91-97.
[4]Mukherjee S P,Maiti S S.Stress-strength reliability in the weibull case[J].Frontiers in Reliability,1998,4:231-248.
[5]Kundu D,Gupta R D.Estimation of p[yzed exponential distribution[J].Metrika,2005,61(3):291-308.
[6]Gupta R D,Kundu D.Generalized logistic distributions[J].Journal of Applied Statistical Science,2010,18(1):51.
[7]Kundu D,Gupta R D.Estimation of p(y [8]Valiollahi R,Asgharzadeh A,Raqab M Z.Estimation of p(ymmunications in Statistics-Theory and Methods,2013,42(24):4476-4498.
[9]Jia Xiang,Nadarajah S,Guo Bo.Bayes estimation of p(ymeters[J].Applied Mathematical Modelling,2017,47(Supplement C):249-259.
[10]Gilks W R,Best N G,Tan K K C.Adaptive rejection metropolis sampling within gibbs sampling[J].Journal of the Royal Statistical Society,Series C(Applied Statistics),1995,44(4):455-472.
[11]Martino L,M′?guez J.A generalization of the adaptive rejection sampling algorithm[J].Statistics and Computing,2011,21(4):633-647.
[12]Frechet M.Sur la loi de probabilite de l’ecart maximum[J].Ann de la Soc Polonaise de Math,1927,6:93-116.
[13]Rosin P.The laws governing the fineness of powdered coal[J].J Inst Fuel,1933,7:29-36.
[14]Herbert A David,Nagaraja H N.Order statistics[M].3rd Edition,Hoboken:Wiley,2003.
[15]Arnold B C,Balakrishnan N.Relations,bounds,and approximations for order statistics[A].Lecture Notes in Statistics[C].1989,53.
[16]Efron B,Efron B.The Jackknife,the Bootstrap and Other Resampling Plans[M].Philadelphia:SIAM,1982.
[17]Hall P.Theoretical comparison of bootstrap confidence intervals[J].The Annals of Statistics,1988,16(3):927-953.
[18]Berger J O,Sun Dongchu.Bayesian analysis for the poly-weibull distribution[J].Journal of the American Statistical Association,1993,88(424):1412-1418.
[19]Gilks W R,Richardson S,Spiegelhalter D J.Introducing markov chain monte carlo[J].Markov chain Monte Carlo in practice,1996,1:19.
[20]Upadhyay S K,Gupta A.A bayes analysis of modified weibull distribution via markov chain monte carlo simulation[J].Journal of Statistical Computation and Simulation,2010,80(3):241-254.
[21]Chen Minghui,Shao Qiman.Monte carlo estimation of bayesian credible and hpd intervals[J].Journal of Computational and Graphical Statistics,1999,8(1):69-92.
[22]Liang Faming,Liu Chuanhai,Carroll R J.Advanced Markov Chain Monte Carlo Methods:Learning from Past Samples[M].Chichester:Wiley,2010.
[23]Liu Jun S.Monte Carlo Strategies in Scientific Computing[M].New York:Springer,2008.
[24]Andrieu C,Thoms J.A tutorial on adaptive mcmc[J].Statistics and Computing,2008,18(4):343-373.
[25]Griffin J E,Walker S G.On adaptive metropolis-hastings methods[J].Statistics and Computing,2013,23(1):123-134.
[26]Cai Bo,Meyer R,Perron F.Metropolis-hastings algorithms with adaptive proposals[J].Statistics and Computing,2008,18(4):421-433.
[27]Bader M G,Priest A M.Statistical aspects of fibre and bundle strength in hybrid composites[A].In:Hayashi T,Kawata K,Umekawa S,eds.,Progress in science and engineering of composites[C].pages 1129-1136,1982.
[28]Raqab M Z,Kundu D.Comparison of different estimators of p[ymmunications in Statistics-Simulation and Computation,2005,34(2):465-483.
[29]Kundu D,Raqab M Z.Estimation of r=p(ymeter weibull distribution[J].Statistics&Probability Letters,2009,79(17):1839-1846.
[30]Surles J G,Padgett W J.Inference for reliability and stress-strength for a scaled burr type x distribution[J].Lifetime Data Analysis,2001,7(2):187-200.