Effects of non-normality on the power function in a one-way random model

The effects of non-normality on type-I and type-II errors in a one-way random model are investigated for moderate departures from normality. It is found that the probabilities of both errors are more sensitive to the kurtosis of between group effects than that of within group effects.     

中华书局版《四书章句集注》点校释误(二)

中华书局1983年版《四书章句集注》的点校存在问题有三:一是由于对引文疏于上溯原文的考证,导致对引文及引文中的引文界定不清;二是朱子在注解《四书》的过程中,非单纯甄别、选用原文,他在对原文进行择选后又加以精心改动,附以点评,对于朱子点评部分书局版并未加以区分;三是还存在漏加前后引号及引号标记错误、漏加书名号及书名号标记错误、专有名词标记错误等问题。     

提高编校注意力探析

注意力是编校过程中重要的心理因素 ,直接影响编辑质量。应从利用有意注意 ,保持职业敏感 ;对编校差错进行分类 ,合理分配注意 ;选择注意 ,要有所为 ,有所不为 ;认准编校目标 ,培养注意稳定性等方面提高编校人员的注意力。     

论名牌产品的自主创新

抢占国际竞争的战略制高点关键靠核心技术,而核心技术必须是自主创新,它是创造名牌产品的关键。在构建社会主义和谐社会的今天,创造名牌产品是切实提高自主创新能力和国际竞争力的集中表现,是改善人民生活的需要,我国实施名牌战略中有几个误区,也有许多发展名牌产品的有利条件。建立争创名牌的企业内在环境和自主创新机制,坚持企业主体公平和合理的竞争原则等是名牌产品自主创新的措施。     

关于电阻测量几种方法的讨论

本文对电阻的测量方法及误差修正进行了比较和分析，并给出合理、直观、简捷的实验测试手段。     

M-Estimates of regression when the scale is unknown and the error distribution is possibly asymmetric: A minimax result

Huber (1964) found the minimax-variance M-estimate of location under the assumption that the scale parameter is known; Li and Zamar (1991) extended this result to the case when the scale is unknown. We consider the robust estimation of the regression coefficients (β₁,…,β_p) when the scale and the intercept parameters are unknown. The minimax-variance estimates of (β₁,…,β_p) with respect to the trace of their asymptotic covariance matrix are derived. The maximum is taken over ?-contamination neighbourhoods of a central regression model with Gaussian errors (asymmetric contamination is allowed), and the minimum is taken over a large class of generalized M-estimates of regression of the Mallow type. The optimal choice of estimates for the nuisance parameters (scale and intercept) is also considered.     

Learning from the Piper Alpha Accident: A Postmortem Analysis of Technical and Organizational Factors

The accident that occurred on board the offshore platform Piper Alpha in July 1988 killed 167 people and cost billions of dollars in property damage. It was caused by a massive fire, which was not the result of an unpredictable "act of God" but of an accumulation of errors and questionable decisions. Most of them were rooted in the organization, its structure, procedures, and culture. This paper analyzes the accident scenario using the risk analysis framework, determines which human decision and actions influenced the occurrence of the basic events, and then identifies the organizational roots of these decisions and actions. These organizational factors are generalizable to other industries and engineering systems. They include flaws in the design guidelines and design practices (e.g., tight physical couplings or insufficient redundancies), misguided priorities in the management of the tradeoff between productivity and safety, mistakes in the management of the personnel on board, and errors of judgment in the process by which financial pressures are applied on the production sector (i.e., the oil companies' definition of profit centers) resulting in deficiencies in inspection and maintenance operations. This analytical approach allows identification of risk management measures that go beyond the purely technical (e.g., add redundancies to a safety system) and also include improvements of management practices.     

Consistent Estimation of the Regression Coefficient Through Weighted Arithmetic Mean of the Inconsistent Estimators in Replicated Ultrastructural Model

The problem of consistent estimation of the slope parameter in an ultrastructural model with replicated observations is considered in this article. A consistent estimator based on a weighted arithmetic mean of two inconsistent least squares estimators is proposed which is independent of any unknown quantity. The efficiency properties of this estimator are studied.     

Estimating spatial means with an application to remotely sensed data

The paper examines alternative estimators for the mean of a spatial process where observations are not independent. Properties of the sample mean and its standard error are contrasted with those of maximum likelihood estimators derived for three spatial models. The information loss caused by spatial dependency in the data is examined. The distribution theory for the estimators is reviewed and the paper concludes with an empirical example illustrating the properties of the estimators and the practical benefits of the maximum likelihood procedure.     

Prediction Performance of Correlated Error Procedures for Spatial Counts

Abstract

Few guidelines exist for the application of geostatistical methods to spatial counts and the prediction to unsampled areas is an important aspect of experimental field research. The prediction performances of kriging and a correlated errors Poisson model are compared through simulation. Counts with a known spatial covariance structure are generated in an investigation involving several factors: area size, overall mean, range of correlation, spatial covariance function, and the presence of trend. The correlated errors Poisson model generally gives superior prediction performance when an exponential covariance structure is used.