Estimation in stratified random sampling: Adjustment for changes in strata composition

Panel studies are widely used to collect data on consumer expenditures, labor force participation and other demographic variables. Frequently, the population changes significantly over the period of interest. We consider the case when a stratified random sample is drawn with probability proportional to initial size (pps) and the value of one of the stratification factors changes over time. Information on such changes, which result in the movement of primary units from their original strata to new strata, is readily available for the sampled units but not for the nonsampled units. As a result of changes in the composition of strata, the stratified sample no longer corresponds to a pps selection within each stratum. A method of estimation based on the original selection of the sample but which incorporates the subsequent changes is proposed. It is shown that these estimates are approximately unbiased. An earlier version of this paper was presented at the 1978 ASA Meetings (Jain [3]).     

Arc refractor methods for adaptive importance sampling on large Bayesian networks under evidential reasoning

Approximate Bayesian inference by importance sampling derives probabilistic statements from a Bayesian network, an essential part of evidential reasoning with the network and an important aspect of many Bayesian methods. A critical problem in importance sampling on Bayesian networks is the selection of a good importance function to sample a network’s prior and posterior probability distribution. The initially optimal importance functions eventually start deviating from the optimal function when sampling a network’s posterior distribution given evidence, even when adaptive methods are used that adjust an importance function to the evidence by learning. In this article we propose a new family of Refractor Importance Sampling (RIS) algorithms for adaptive importance sampling under evidential reasoning. RIS applies “arc refractors” to a Bayesian network by adding new arcs and refining the conditional probability tables. The goal of RIS is to optimize the importance function for the posterior distribution and reduce the error variance of sampling. Our experimental results show a significant improvement of RIS over state-of-the-art adaptive importance sampling algorithms.     

Augmented line sampling for approximation of failure probability function in reliability-based analysis

An efficient approach, called augmented line sampling, is proposed to locally evaluate the failure probability function (FPF) in structural reliability-based design by using only one reliability analysis run of line sampling. The novelty of this approach is that it re-uses the information of a single line sampling analysis to construct the FPF estimation, repeated evaluations of the failure probabilities can be avoided. It is shown that, when design parameters are the distribution parameters of basic random variables, the desired information about FPF can be extracted through a single implementation of line sampling. Line sampling is a highly efficient and widely used reliability analysis method. The proposed method extends the traditional line sampling for the failure probability estimation to the evaluation of the FPF which is a challenge task. The required computational effort is neither relatively sensitive to the number of uncertain parameters, nor grows with the number of design parameters. Numerical examples are given to show the advantages of the approach.     

Research on Inference of Candidate Database Web Surveys Based on Superpopulation Pseudo Design and the Combined Sample

How to solve the inference problem of candidate database web surveys is an urgent problem to be solved in the development of web survey. In order to solve this problem, the inference method of non-probability sampling based on superpopulation pseudo design and the combined sample is proposed. A superpopulation model is firstly built up to construct pseudo weights for a survey sample of the web candidate database. The estimator of the population mean is then computed according to the combined sample composed of the survey sample of the web candidate database and a probability sample. The variance estimator of the population mean estimator is lastly derived according to the variance estimation theory of the superpopulation model. The Bootstrap and Jackknife methods are also used to compute the variance estimator. And all these variance estimation methods are compared. The research results show that the population mean estimator based on superpopulation pseudo design and the combined sample is better, and has higher efficiency than the estimator only using the probability sample and the weighted estimator only using the survey sample of the web candidate database. The variance estimator computed by using the VM1, VM2 and VM3 method are relatively better.     

���ڳ�����α�������������ĺ�ѡ�����ݿ����������ƶ��о�

??How to solve the inference problem of candidate database web surveys is an urgent problem to be solved in the development of web survey. In order to solve this problem, the inference method of non-probability sampling based on superpopulation pseudo design and the combined sample is proposed. A superpopulation model is firstly built up to construct pseudo weights for a survey sample of the web candidate database. The estimator of the population mean is then computed according to the combined sample composed of the survey sample of the web candidate database and a probability sample. The variance estimator of the population mean estimator is lastly derived according to the variance estimation theory of the superpopulation model. The Bootstrap and Jackknife methods are also used to compute the variance estimator. And all these variance estimation methods are compared. The research results show that the population mean estimator based on superpopulation pseudo design and the combined sample is better, and has higher efficiency than the estimator only using the probability sample and the weighted estimator only using the survey sample of the web candidate database. The variance estimator computed by using the VM1, VM2 and VM3 method are relatively better.     

On a general class of probability distributions and its applications

A general class of probability distributions is proposed and its properties examined. The proposed family contains distributions of a wide variety of shapes, such as U shaped, uniform and long-tailed distributions, as well as distributions with supports that have finite limits at one or both endpoints. Due to its great flexibility, this parametric class (which we refer to as the class of UIC distributions) can be routinely used to fit empirical data collected in different experimental or observational studies without the need of specifying in prior the type and form of distributions to be fitted. It is also simple and inexpensive to simulate from the proposed class of distributions, making it particularly attractive in simulation based optimization applications involving stochastic components with distributions empirically determined from historical data. More importantly, it is shown both theoretically and empirically that under fairly general conditions the sampling distribution of a standardized sample statistic is approximately an UIC distribution, which provides a much closer approximation than the normal approximation in small to medium sample sizes. Applications in the bootstrap, such as estimation of the variance of sample quantiles and quantile estimation by the “smoothed” bootstrap are discussed. The Monte Carlo studies conducted show encouraging results, even in cases where the traditional kernel density approximations do not perform well.     

Hazard function estimation with cause-of-death data missing at random

Hazard function estimation is an important part of survival analysis. Interest often centers on estimating the hazard function associated with a particular cause of death. We propose three nonparametric kernel estimators for the hazard function, all of which are appropriate when death times are subject to random censorship and censoring indicators can be missing at random. Specifically, we present a regression surrogate estimator, an imputation estimator, and an inverse probability weighted estimator. All three estimators are uniformly strongly consistent and asymptotically normal. We derive asymptotic representations of the mean squared error and the mean integrated squared error for these estimators and we discuss a data-driven bandwidth selection method. A simulation study, conducted to assess finite sample behavior, demonstrates that the proposed hazard estimators perform relatively well. We illustrate our methods with an analysis of some vascular disease data.     

����ȱʧ���ݵ�B������ָ��ģ�͹���

??In this paper, we studied the inverse probability weighted least squares estimation of single-index model with response variable missing at random. Firstly, the B-spline technique is used to approximate the unknown single-index function, and then the objective function is established based on the inverse probability weighted least squares method. By the two-stage Newton iterative algorithm, the estimation of index parameters and the B-spline coefficients can be obtained. Finally, through many simulation examples and a real data application, it can be concluded that the method proposed in this paper performs very well for moderate sample     

Estimating completion-time distribution in stochastic activity networks

This paper deals with simulation-based estimation of the probability distribution for completion time in stochastic activity networks. These distribution functions may be valuable in many applications. A simulation method, using importance-sampling techniques, is presented for estimation of the probability distribution function. Separating the state space into two sets, one which must be sampled and another which need not be, is suggested. The sampling plan of the simulation can then be decided after the probabilities of the two sets are adjusted. A formula for the adjustment of the probabilities is presented. It is demonstrated that the estimator is unbiased and the upper bound of variance minimized. Adaptive sampling, utilizing the importance sampling techniques, is discussed to solve problems where there is no information or more than one way to separate the state space. Examples are used to illustrate the sampling plan.     

A novel fractional moments-based maximum entropy method for high-dimensional reliability analysis

High-dimensional reliability analysis is still an open challenge in structural reliability community. To address this problem, a new sampling approach, named the good lattice point method based partially stratified sampling is proposed in the fractional moments-based maximum entropy method. In this approach, the original sample space is first partitioned into several orthogonal low-dimensional sample spaces, say 2 and 1 dimensions. Then, the samples in each low-dimensional sample space are generated by the good lattice point method, which are deterministic points and possess the property of large variance reduction. Finally, the samples in the original space can be obtained by randomly pairing the samples in low-dimensions, which may also significantly reduce the variance in high-dimensional cases. Then, this sampling approach is applied to evaluate the low-order fractional moments in the maximum entropy method with the tradeoff of efficiency and accuracy for high-dimensional reliability problems. In this regard, the probability density function of the performance function involving a large number of random inputs can be derived accordingly, where the reliability can be straightforwardly evaluated by a simple integral over the probability density function. Numerical examples are studied to validate the proposed method, which indicate the proposed method is of accuracy and efficiency for high-dimensional reliability analysis.     

Estimation of dependences based on Bayesian correction of a committee of classification algorithms

Estimation of dependence of a scalar variable on the vector of independent variables based on a training sample is considered. No a priori conditions are imposed on the form of the function. An approach to the estimation of the functional dependence is proposed based on the solution of a finite number of special classification problems constructed on the basis of the training sample and on the subsequent prediction of the value of the function as a group decision. A statistical model and Bayes’ formula are used to combine the recognition results. A generic algorithm for constructing the regression is proposed for different approaches to the selection of the committee of classification algorithms and to the estimation of their probabilistic characteristics. Comparison results of the proposed approach with the results obtained using other models for the estimation of dependences are presented.     

Marshall-Olkin�������ֲ��ı�Ҷ˹����

??Kundu and Gupta proposed to use the importance sampling method to compute the Bayesian estimation of the unknown parameters of the Marshall-Olkin bivariate Weibull distribution. However, we find that the performance of the importance sampling method becomes worse as the sample size gets larger. In this paper, we introduce latent variables to simplify the likelihood function, and use MCMC algorithm to estimate the unknown parameters. Numerical simulations are carried out to assess the performance of the proposed method by comparing with the maximum likelihood estimation, and we find that the Bayesian estimates perform better even for the case of small sample size. A real data is also analyzed for illustrative purpose.     

Automated rejection sampling from product of distributions

Summary  Sampling from probability density functions (pdfs) has become more and more important in many areas of applied science, and has therefore been the subject of great attention. Many sampling procedures proposed allow for approximate or asymptotic sampling. On the other hand, very few methods allow for exact sampling. Direct sampling of standard pdfs is feasible, but sampling of much more complicated pdfs is often required. Rejection sampling allows to exactly sample from univariate pdfs, but has the huge drawback of needing a case-by-case calculation of a comparison function that often reveals as a tremendous chore, whose results dramatically affect the efficiency of the sampling procedure. In this paper, we restrict ourselves to a pdf that is proportional to a product of standard distributions. From there, we show that an automated selection of both the comparison function and the upper bound is possible. Moreover, this choice is performed in order to optimize the sampling efficiency among a range of potential solutions. Finally, the method is illustrated on a few examples.     

Improved probabilistic point estimation schemes for uncertainty analysis

The probabilistic point estimation (PPE) methods replace the probability distribution of the random parameters of a model with a finite number of discrete points in sample space selected in such a way to preserve limit probabilistic information of involved random parameters. Most PPE methods developed thus far match the distribution of random parameters up to the third statistical moment and, in general, could provide reasonable accurate estimation only for the first two statistical moments of model output. This study proposes two optimization-based point selection schemes for the PPE methods to enhance the accuracy of higher-order statistical moments estimation for model output. Several test models of varying degrees of complexity and nonlinearity are used to examine the performance of the proposed point selection schemes. The results indicate that the proposed point selection schemes provide significantly more accurate estimation of model output uncertainty features than the existing schemes.     

Threshold variable selection of asymmetric stochastic volatility models

A threshold stochastic volatility (SV) model is used for capturing time-varying volatilities and nonlinearity. Two adaptive Markov chain Monte Carlo (MCMC) methods of model selection are designed for the selection of threshold variables for this family of SV models. The first method is the direct estimation which approximates the model posterior probabilities of competing models. Using parallel MCMC sampling to estimate these probabilities, the best threshold variable is selected with the highest posterior model probability. The second method is to use the deviance information criterion to compare among these competing models and select the best one. Simulation results lead us to conclude that for large samples the posterior model probability approximation method can give an accurate approximation of the posterior probability in Bayesian model selection. The method delivers a powerful and sharp model selection tool. An empirical study of five Asian stock markets provides strong support for the threshold variable which is formulated as a weighted average of important variables.     

基于局部多项式展开的多元非参数模型贝叶斯带宽选择

在多元非参数模型中带宽和阶的选择对局部多项式估计量的表现十分重要。本文基于交叉验证准则提出一个自适应贝叶斯带宽选择方法。在给定的误差密度函数下,该方法可推导出对应的似然函数,并构造带宽参数的后验密度函数。随后,通过带宽的后验期望可同时获得阶和带宽的估计。数值模拟的结果表明,该方法不仅比大拇指准则方法精确,且比交叉验证方法耗时更少。与此同时,与Nadaraya-Watson估计相比,所提带宽选择方法对多元非参数模型的适应性要更好。最后,本文通过一组实际数据说明有限样本下所提贝叶斯带宽选择的表现很好。     

Case-cohort analysis with general additive-multiplicative hazard models

The case-cohort design is widely used in large epidemiological studies and prevention trials for cost reduction. In such a design, covariates are assembled only for a subcohort which is a random subset of the entire cohort and any additional cases outside the subcohort. In this paper, we discuss the case-cohort analysis with a class of general additive-multiplicative hazard models which includes the commonly used Cox model and additive hazard model as special cases. Two sampling schemes for the subcohort, Bernoulli sampling with arbitrary selection probabilities and stratified simple random sampling with fixed subcohort sizes, are discussed. In each setting, an estimating function is constructed to estimate the regression parameters. The resulting estimator is shown to be consistent and asymptotically normally distributed. The limiting variance-covariance matrix can be consistently estimated by the case-cohort data. A simulation study is conducted to assess the finite sample performances of the proposed method and a real example is provided.     

On Random Sampling Without Replacement from a Finite Population

We consider the three progressively more general sampling schemes without replacement from a finite population: simple random sampling without replacement, Midzuno sampling and successive sampling. We (i) obtain a lower bound on the expected sample coverage of a successive sample, (ii) show that the vector of first order inclusion probabilities divided by the sample size is majorized by the vector of selection probabilities of a successive sample, and (iii) partially order the vectors of first order inclusion probabilities for the three sampling schemes by majorization. We also show that the probability of an ordered successive sample enjoys the arrangement increasing property and for sample size two the expected sample coverage of a successive sample is Schur convex in its selection probabilities. We also study the spacings of a simple random sample from a linearly ordered finite population and characterize in several ways a simple random sample.     

基于轮换样本连续性调查的校准组合估计方法研究

校准估计是抽样调查中比较常用的一种利用辅助信息提高估计量精度的方法。回归组合估计量作为轮换样本连续性调查中使用的一种有效的估计量,是可以通过校准程序得到的。基于回归组合估计量和校准程序之间的关系,本文提出了轮换样本连续性抽样调查条件下的不同校准组合估计量及其方差估计。校准组合估计量的主要思想是在校准估计程序中将拼配样本和非拼配样本的辅助信息进行不同的组合利用。本文利用美国现时人口调查的微观数据进行数值模拟,来比较不同校准组合估计量的估计效率,模拟结果表明两步校准组合估计量和两步校准双组合估计量的表现相似,且估计精度都高于H-T估计量及回归组合估计量;而两步校准组合估计量由于其简便性更适合应用于实践中。最后以我国农村住户连续性抽样调查为例,设计一套符合我国实际的轮换样本连续性调查方案,并将提出的校准组合估计量运用于估计阶段,为中国政府统计调查提供一定的借鉴和参考.