利用隐蔽的系统寿命数据估计元件的可靠性

考虑由一个成败型元件和一个指数寿命型元件组成的串联系统。本文利用隐蔽的系统一次性检测数据估计元件的可靠性，给出元件可靠性的极大似然估计和区门估计，给出了算例。     

限制经验似然置信区域的置信概率的精度

证明了用限制经验似然比构造的置信区域的置信概率的阶为Ｏ（ｎ＾－１），使用Ｂａｒｔｌｅｔｔ修正方法将该误差的阶降为Ｏ（ｎ＾－２）。     

Estimating functions for conditional inference: Many nuisance parameter case

When there is a complete sufficient statistic for the nuisance parameter which depends on the parameter of interest then there are locally optimal unbiased estimating functions, but generally there is no globally optimal estimating function. We consider conditioning on the minimal sufficient statistic for the nuisance parameter and find the conditional linear optimal unbiased estimating function. Since the nuisance parameter is totally eliminated in the conditional model there is no intrinsic problem in setting up conditional tests of significance and confidence intervals. A compromise between conditional and unconditional optimum estimating functions is suggested. The techniques are illustrated on three examples including the well known common means problem. The proposed hypothesis testing and confidence interval procedures work reasonably well for the examples considered.     

Fuzzy综合评判在评价教师教学质量工作中的应用

本文应用Ｆｕｚｚｙ综合评判方法及教育测量学知识综合评价教师的教学质量．此法较其它评价方法更客观、细腻、可靠，对教学管理工作具有参考价值．     

Meet,discuss, and segregate!

We present a model of opinion dynamics in which agents adjust continuous opinions as a result of random binary encounters whenever their difference in opinion is below a given threshold. High thresholds yield convergence of opinions toward an average opinion, whereas low thresholds result in several opinion clusters. The model is further generalized to network interactions, threshold heterogeneity, adaptive thresholds, and binary strings of opinions. © 2002 Wiley Periodicals, Inc.     

BOOTSTRAP CRITICAL POINT FOR CIRCULAR MEAN DIRECTION AND ITS APPLICATIONS

ＢＯＯＴＳＴＲＡＰＣＲＩＴＩＣＡＬＰＯＩＮＴＦＯＲＣＩＲＣＵＬＡＲＭＥＡＮＤＩＲＥＣＴＩＯＮＡＮＤＩＴＳＡＰＰＬＩＣＡＴＩＯＮＳＷＵＣＨＡＯＢＩＡＯＡＮＤＤＥＮＧＷＥＩＣＡＩＡｂｓｔｒａｃｔ．Ｆｉｒｓｔｌｙ，ｔｈｉｓｐａｐｅｒｒｅｖｉｅｗｓＨａｌ’...     

A randomly weighted estimate of the population mean

ＡＲＡＮＤＯＭＬＹＷＥＩＧＨＴＥＤＥＳＴＩＭＡＴＥＯＦＴＨＥＰＯＰＵＬＡＴＩＯＮ　ＭＥＡＮＣＨＥＮＸＩＲＵ（陈希孺）ＪＩＮＭＩＮＧＺＨＯＮＧ（金明仲）（ＧｒａｄｕａｔｅＳｃｈｏｏｌ,ＵｎｉｖｅｒｓｉｔｙｏｆＳｃｉｅｎｃｅａｎｄＴｅｃｈｎｏｌａｐｙｏｆ...     

When not to analyze data: Decision making on missing responses in dual scaling

In exploratory data analysis, handling of missing responses requires special considerations because of the absence of a model for them. This study investigates effects of missing responses on dual scaling results, in particular a practical decision rule when to and not to impute for missing responses. More specifically, three questions are asked: when to discard a subject, when to exclude a variable, and when to stop data analysis entirely. The decision rule is based on the concept of substantial discrepancy in the scaling outcome between the best and worst imputations for missing responses. This problem is discussed in the context of the current knowledge on missing responses in data analysis.     

Identification of an enantiotropic system with hindered multiphase transitions

Some preliminary considerations suggest that the so-called ‘compensation law’ is a result of the misinterpretation of evaluation procedure. The both parameters: pre-exponential factor and activation energy are calculated from the same set of experimental data. A confidence ellipse could describe the precision of these parameters. In the case of using the least square method for straight-line parameters evaluation, we could calculate a axes of the ellipse, using experimental data. If the observed relationship between pre-exponential factor and activation energy agree with the ‘pre-calculated’ direction of main axis of confidence ellipse, we have a strong support to believe that the observed ‘compensation’ effect is only an artificial effect of misinterpretation. Some calculations performed for a published experimental data have confirmed these suspicions. This also, indirectly indicates that precision of such experiments is probably lower than expected.     

Nonparametric estimation of operational value-at-risk (OpVaR)

This paper introduces nonparametric methods for estimating 99.9% operational value-at-risk (OpVaR) and its confidence interval (CI), and demonstrates their applications to US business losses. An attractive feature of these new methods is that there is no need to estimate either the entire heavy-tailed loss distribution or the tail region of the distribution. Furthermore, we provide algorithms that facilitate applied researchers and practitioners in risk management area to implement the sophisticated empirical likelihood ratio (ELR) based methodologies to construct the CI of the true underlying 99.9% OpVaR. In a simulation study, we find that the weighted ELR (WELR) CI estimator is more reliable than the ELR CI estimator. The empirical results show that the nonparametric OpVaR estimates are consistently larger than those of other comparable methods, which provide adequate regulatory capitals, particularly during crises. The findings have implications for regulators, and effective and efficient risk financing.