Superiority of the r–k Class Estimator Over Some Estimators In A Linear Model

In regression analysis, to overcome the problem of multicollinearity, the r ? k class estimator is proposed as an alternative to the ordinary least squares estimator which is a general estimator including the ordinary ridge regression estimator, the principal components regression estimator and the ordinary least squares estimator. In this article, we derive the necessary and sufficient conditions for the superiority of the r ? k class estimator over each of these estimators under the Mahalanobis loss function by the average loss criterion. Then, we compare these estimators with each other using the same criterion. Also, we suggest to test to verify if these conditions are indeed satisfied. Finally, a numerical example and a Monte Carlo simulation are done to illustrate the theoretical results.     

Living Environment Preferences of the Inhabitants of Istanbul: A Modified Hierarchical Information Integration Model

This paper presents a two-stage research to model the different priorities and expectations about living environment preferences of the inhabitants of Istanbul, Turkey's largest metropolitan with a population of 10 million. In the first stage, a modified hierarchical information integration approach was used to estimate the utilities of different attributes for each individual sampled from the inhabitants of Istanbul. This is a decompositional approach and involves measuring individual preferences. In this study, not only aggregate results are reported but also a segmentation study is carried out to explore the heterogeneity in respondents' preferences. Identification of such segments would help planner offer different planning options to groups with different preferences. Thus, the second stage of this study consists of identifying distinct groups of inhabitants with different preference structures by using cluster analysis. The resulting information is believed to be more useful especially to understand diverging demands of inhabitants of Istanbul.     

Evaluation of simple dispatching rules for dynamic single-machine earliness/tardiness problem

Abstract. This paper investigates the effects of four simple dispatching rules on just-in-time production related performance measures of mean and maximum absolute lateness. The rules used are modified due date (MDD), shortest processing time (SPT), earliest due date (EDD), and first in first out (FIFO). A single machine is used under three utilization levels. Due-dates are set according to total work content rule. The results indicate that each rule performs well under certain conditions. The MDD rule is the best one to minimize mean absolute lateness. The EDD and FIFO rules do well in minimizing the maximum absolute lateness. Economic interpretation of these performance measures are also discussed.     

A possibilistic aggregate production planning model for brass casting industry

This article discusses a possibilistic aggregate production planning (APP) model for blending problem in a brass factory; the problem computing optimal amounts of raw materials for the total production of several types of brass in a planning period. The model basically has a multi-blend model formulation in which demand quantities, percentages of the ingredient in some raw materials, cost coefficients, minimum and maximum procurement amounts are all imprecise and have triangular possibility distributions. A mathematical model and a solution algorithm are proposed for solving this model. In the proposed model, the Lai and Hwang's fuzzy ranking concept is relaxed by using ‘Either-or’ constraints. An application of the brass casting APP model to a brass factory demonstrates that the proposed model successfully solves the multi-blend problem for brass casting and determines the optimal raw material purchasing policies.     

Modified and Restricted r-k Class Estimators

In this article, we introduce the modified r-k class estimator and the restricted r-k class estimator. We compare the performances of the new estimators to the r-k class estimator with respect to the matrix mean square error (MSE) criterion. As a special case of the restricted r-k class estimator, we obtain the restricted principal components regression (RPCR) estimator. Finally, we conduct a Monte Carlo simulation study and a numerical example to investigate the performances of the proposed estimators by the scalar mean square error (mse) criterion.     

Collaboration in genocide: the Ottoman Empire 1915–1916, the German-occupied Baltic 1941–1944, and Rwanda 1994

This article develops a new paradigm for the study of collaboration by applying the concept to events outside the context of the Second World War. The authors examine three instances of collaboration in twentieth-century mass killings, seeking to situate them within the framework of genocide. Using a multidisciplinary approach, the article questions the validity of explanations of conflict predicated on the existence of binary systems—explanations that appear frequently in comparative genocide studies. The authors relate the decision to participate in mass murder to the history of structural inequality within a given society. The article concludes that, however vague, the concept of collaboration is useful in accentuating a bottom-up approach in the study of genocide.     

GIM and logistics in the factory of the future

Abstract

In the future, the competitive strength of industry will depend on its ability to realize flexible production systems, to install intelligent EDP-systems and to link them to a goal-orientated logistic system. Currently, a lot of new strategies, concepts and approaches for production arc being promoted and discussed, often in a spirit of controversy: CIM (computer integrated manufacturing), 'production logistics’, and JIT (just-in-time production) have become familiar concepts which have one thing in common: new structures in production will be necessary. However, the overall effect of CIM is often very small in comparison to the investment for realizing this concept. The main reason is that such projects are missing a logistic orientation. A continuous flow of information and material as envisaged by the logistics principle requires not only that all automation components can be integrated on the technical level, but also that all relevant functions and sectors can be integrated organizationally.     

工程科技创新的人才培养模式研究——澳大利亚查尔斯特大学的启示

工程科技是改变世界重要力量。我国高校工科人才培养是高等教育的重要组成部分,肩负着为国家重大工程科技攻关培养建设者和接班人的重任。在全球范围内,随着新一轮科技革命和产业变革加速演进,以人工智能、大数据为代表的新一代信息技术的快速发展,正在对传统工程教育的人才培养理念、课程设计和教学模式产生革命性影响。工程教育改革已成为高等学校教育改革的热点,各国纷纷出台政策文件以适应现代化工程科技创新对人才培养的需求。文章采用结构化案例,通过分析全球工程教育“新兴领导者”澳大利亚查尔斯特大学工程本科生的培养理念、课程设计和教学模式,为面向工程科技创新的我国高等学校工程人才培养提供了参考。比如要重视产学研资源汇聚,探索服务区域经济发展新模式;构建“工程知识三角”嵌入联动机制,实现创新型工程人才培养;开发多维度教育资源,创设开放融合的“线上+线下”学习生态圈;强化跨学科平台会聚,连接不同学习场景促进工程知识融通。文章为提出面向新时代我国工程科技创新的工程教育改革和人才培养模式提供了借鉴。      

Rubbery Polya Tree

Abstract. Polya trees (PT) are random probability measures which can assign probability 1 to the set of continuous distributions for certain specifications of the hyperparameters. This feature distinguishes the PT from the popular Dirichlet process (DP) model which assigns probability 1 to the set of discrete distributions. However, the PT is not nearly as widely used as the DP prior. Probably the main reason is an awkward dependence of posterior inference on the choice of the partitioning subsets in the definition of the PT. We propose a generalization of the PT prior that mitigates this undesirable dependence on the partition structure, by allowing the branching probabilities to be dependent within the same level. The proposed new process is not a PT anymore. However, it is still a tail‐free process and many of the prior properties remain the same as those for the PT.