结构可靠性分析中蒙特卡洛模拟的应用

本文讨论了蒙特卡洛模拟在结构可靠性分析中的应用 ,并给出了直接抽样法中失效概率的计算公式和置信区间     

基于分层随机抽样的季节指数的抽样估计研究

由于传统的季节指数分析方法是一种描述统计,本文提出了采用分层随机抽样的季节指数估计量,给出了估计量的偏误和均方误差以及均方误差的估计,并在此基础上分析了季节指数的假设检验以及最优估计量的确定。     

Non-parametric Bayesian Inference for Integrals with respect to an Unknown Finite Measure

Abstract.  We consider the problem of estimating a collection of integrals with respect to an unknown finite measure μ from noisy observations of some of the integrals. A new method to carry out Bayesian inference for the integrals is proposed. We use a Dirichlet or Gamma process as a prior for μ , and construct an approximation to the posterior distribution of the integrals using the sampling importance resampling algorithm and samples from a new multidimensional version of a Markov chain by Feigin and Tweedie. We prove that the Markov chain is positive Harris recurrent, and that the approximating distribution converges weakly to the posterior as the sample size increases, under a mild integrability condition. Applications to polymer chemistry and mathematical finance are given.     

A List Sequential Sampling Method Suitable for Real-Time Sampling

Abstract.  A flexible list sequential π ps sampling method is introduced and studied. It can reproduce any given sampling design without replacement, of fixed or random sample size. The method is a splitting method and uses successive updating of inclusion probabilities. The main advantage of the method is in real-time sampling situations where it can be used as a powerful alternative to Bernoulli and Poisson sampling and can give any desired second-order inclusion probabilities and thus considerably reduce the variability of the sample size.     

A procedure for selection of a gamma-Poisson single sampling plan by attributes

Design and evaluation of sampling plans by attributes and by variables are important aspects in the area of acceptance sampling research. Various procedures for the selection of conventional single sampling by attributes have been developed and are available in the literature. This paper presents a design methodology and tables for the selection of parameters of single sampling plans for specified requirements (strengths) under the conditions of a gamma prior and Poisson sampling distribution. The relative efficiency of gamma-Poisson single sampling plans over conventional plans is discussed through empirical illustrations.     

分层抽样下的样本轮换理论研究

讨论用于回归估计的二相抽样理论在分层抽样下样本轮换后估计量的构造及其精度问题,并在构造的估计量的基础上计算了分层抽样下的最优样本轮换率,这对于深入研究分层抽样理论,使其估计量的精度提高,从而更好地实现抽样调查的目标有积极意义。     

Use of Risk Assessment Methods in the Certification of Decontaminated Buildings

Accidental events such as fires, explosions, and leaks often result in large-scale contaminations of buildings with toxic chemicals. After decontamination, the certification for original use requires testing for residual contamination. The two basic kinds of sampling plans in use up to recently both fall short of the required performance. Their deficiencies are analyzed in terms of the scientific questions implicit in both the sampling plan and the subsequent statistical evaluation. A sampling strategy of a new kind is proposed and discussed in the same context. It is motivated by concern for the long-term safety of the building's occupants and is, therefore, based on factors important in risk assessment. Three different sampling plans are derived in the framework of this methodology, two of which have already been used in actual certification proceedings.     

Sample size choice for reliability verification in strength-stress models

This paper discusses the choice of sample size for experiments concerned with inference on R = P(Y < X), where X and Y are normal variates, in an acceptance-sampling-theory framework. A conservative approach is derived, and the properties of this solution examined by simulation.     

Verifying zero-infestation in pest control: A simple sequential test based on the succession of zero-samples

Summary A simple sequential test based on the succession of ‘zero's or uninfested sampling units is proposed for use in verifying zero-infestation in pest control surveys. The method is applicable efficiently to both finite and infinite populations. Problems concerning its efficiency on application are discussed.