Accurate computation of single and product moments of order statistics under progressive censoring

An accurate procedure is proposed to calculate approximate moments of progressive order statistics in the context of statistical inference for lifetime models. The study analyses the performance of power series expansion to approximate the moments for location and scale distributions with high precision and smaller deviations with respect to the exact values. A comparative analysis between exact and approximate methods is shown using some tables and figures. The different approximations are applied in two situations. First, we consider the problem of computing the large sample variance–covariance matrix of maximum likelihood estimators. We also use the approximations to obtain progressively censored sampling plans for log-normal distributed data. These problems illustrate that the presented procedure is highly useful to compute the moments with precision for numerous censoring patterns and, in many cases, is the only valid method because the exact calculation may not be applicable.     

Proportional reversed hazard rate model and its applications

The purpose of this paper is to study the structure and properties of the proportional reversed hazard rate model (PRHRM) in contrast to the celebrated proportional hazard model (PHM). The monotonicity of the hazard rate and the reversed hazard rate of the model is investigated. Some criteria of aging are presented and the inheritance of the aging notions (of the base distribution) by the PRHRM is studied. Characterizations of the model involving Fisher information are presented and the statistical inference of the parameters is discussed. Finally, it is shown that several members of the proportional reversed hazard rate class have been found to be useful and flexible in real data analysis.     

On calculating the fisher information in order statistics

This article gives a simple result for the expression of the Fisher information in order statistics. This result enables us to calculate easily the Fisher information in any set of order statistics whose details have been known to be messy and complicated. We consider here its application in the optimal spacing problem where the exact Fisher information in order statistics has been approximated with the asymptotic information or the reciprocal of the variance of a suitable estimator. This work was supported by Korea Research Foundation Grant(KRF-2000-015-DP0056)     

用数学函数分析法对统计指数因素分析的进一步改良——谈综合指数体系的缺陷与消除

指数因素分析法是一种重要的统计分析方法,而其分析结果的正确与否取决于所用的指数体系。利用传统的综合指数体系从事因素分析虽方便,使用,但也存在一些不足。本文提出用其他指数体系进行因素分析的思想,以弥补传统综合指数体系在因素分析中的缺陷。     

上市公司“庄股跳水”预测模型的实证分析

预防"庄股跳水"是投资者在中国股市中生存的必修课,同时也是股市行为研究的难点之一.本文选取2000年到2003年深市遭遇跳水行情的股票及与之相对应的非跳水股票各31只股票为样本,运用t检验、判别分析和主成分分析等多种计量方法和模型对两类股票的各种重要指标进行了详细分析、比较及预测.实证研究发现两类股票的各种重要指标存在重大差异,并且模型能够以较高的准确率预测"庄股跳水".     

不同模型在财务预警实证中的比较研究

研究当前国内外公司财务困境预测问题的现状,寻找一套适合于我国企业的财务状况识别指标体系;然后依据该指标体系采用不同方法建立财务状况预测模型;最后,利用样本公司实际指标数据对各个模型的短期及中期预测效果进行了比较分析与实证研究。     

Asymptotic relative efficiency of the linear discriminant function under partial nonrandom classification of the training data

This paper considers the problem where the linear discriminant rule is formed from training data that are only partially classified with respect to the two groups of origin. A further complication is that the data of unknown origin do not constitute an observed random sample from a mixture of the two under- lying groups. Under the assumption of a homoscedastic normal model, the overall error rate of the sample linear discriminant rule formed by maximum likelihood from the partially classified training data is derived up to and including terms of the first order in the case of univariate feature data. This first- order expansion of the sample rule so formed is used to define its asymptotic efficiency relative to the rule formed from a completely classified random training set and also to the rule formed from a completely unclassified random set.     

Multilevel maximum likelihood estimation with application to covariance matrices

The asymptotic variance of the maximum likelihood estimate is proved to decrease when the maximization is restricted to a subspace that contains the true parameter value. Maximum likelihood estimation allows a systematic fitting of covariance models to the sample, which is important in data assimilation. The hierarchical maximum likelihood approach is applied to the spectral diagonal covariance model with different parameterizations of eigenvalue decay, and to the sparse inverse covariance model with specified parameter values on different sets of nonzero entries. It is shown computationally that using smaller sets of parameters can decrease the sampling noise in high dimension substantially.     

Identifying Changing Aviation Threat Environments Within an Adaptive Homeland Security Advisory System

A critical component of aviation security consists of screening passengers and baggage to protect airports and aircraft from terrorist threats. Advancements in screening device technology have increased the ability to detect these threats; however, specifying the operational configurations of these devices in response to changes in the threat environment can become difficult. This article proposes to use Fisher information as a statistical measure for detecting changes in the threat environment. The perceived risk of passengers, according to prescreening information and behavior analysis, is analyzed as the passengers sequentially enter the security checkpoint. The alarm responses from the devices used to detect threats are also analyzed to monitor significant changes in the frequency of threat items uncovered. The key results are that this information‐based measure can be used within the Homeland Security Advisory System to indicate changes in threat conditions in real time, and provide the flexibility of security screening detection devices to responsively and automatically adapt operational configurations to these changing threat conditions.