Equating of multi-facet tests across administrations

The purpose of this study is to explore criteria for common element test equating for performance examinations. Using the multi-facet Rasch model, each element of each facet is calibrated or placed in a relative position on a Benchmark or reference scale. Common elements from each facet, included on the examinations being equated, are used to anchor the facet elements to the Benchmark Scale. This places all examinations on the same scale so that the same criterion standard can be used. Performance examinations typically have three to four facets including examinees, raters, items and tasks. Raters rate examinees on tasks related to the items included in the test. The initial anchoring of a current test administration to the Benchmark Scale is evaluated for invariance and fit. If there is too much variance or lack of fit for particular facet elements, it may be necessary to unanchor those elements, which means they are not used in the equating. The equating process was applied to an exam with four facets and another with five facets. Results found few common facet elements that could not be used in the test equating process and that differences in the difficulty of the equated exams were identified so that the criterion standard on the Benchmark Scale could be used. It was necessary to use careful quality control for anchoring the common elements in each facet. The common elements should be unaltered from their original use. Strict criteria for displacement and fit must be established and used consistently. Unanchoring inconsistent and/or misfitting facet elements improves the quality of the test equating.     

Equating rehabilitation outcome scales: developing common metrics

Transparency with regard to measuring devices is one of the fundamental requirements for progress in science. The ability to derive comparable measures from different measuring devices is the cornerstone of transparency. To this end, progress in measuring and understanding rehabilitation outcomes requires that there is a method of measuring outcomes that is independent of the particular collection of items that is used to assess the outcomes. The purpose of this study is to develop a equivalence between the PECS Motor Skills and Cognition and Communication LifeScales with the FIM Motor Skills and Cognitive items. However, only the results of the Motor Skills Scale are reported here in the interest of brevity. This equating is based on approximately 500 simultaneous evaluations using bout the PECS and FIM scales on admission and discharge. The patients in this study were consecutive admissions to a free-standing rehabilitation hospital in early 1998. Patients from five diagnostic groups were included in this study, Brain Injury, Spinal Cord Injury, Stroke, Neuromuscular, and Musculoskeletal. The results indicate that it is possible to construct a common equal interval translation between the PECS and FIM for the two scales. Measures on the common metric can be based to either scale and are independent of the number of items completed. This use of these anchored scales will allow institutions using either the PECS and FIM to make direct comparisons of clinical outcomes with other institutions, independent of the particular outcome tool used to evaluate patients.     

Equating and item banking with the Rasch model

This article describes Rasch measurement procedures for equating multiple test forms or calibrating an item bank. The procedures entail (a) selecting an appropriate data collection design, (b) estimating parameters, (c) transforming the parameters from multiple forms to a common scale, and (d) evaluating the quality of the linkage between these forms. Data collection designs include (a) anchor tests, (b) single group, (c) single data set, and (d) equivalent groups. Estimation procedures may involve (a) separate or (b) simultaneous calibration of data from multiple forms. Transformation is typically accomplished using (a) estimation scaling, but may involve (b) parameter anchoring or (c) computing equating constants. Link quality is evaluated using four fit indices: (a) item-within-link, (b) item-between-link, (c) link-within-bank, and (d) form-within-bank. These procedures are illustrated using an anchor test design.     

A Comparison of Equating Methods and Linking Designs for Developing an Item Pool under Item Response Theory

The existence of an item pool can bring out the various merits of using item response theory (IRT). This study considered the case where the development of an item pool is in progress. We examined the robustness of four calibration methods in three linking designs using simulated data. The data were generated assuming that a small-sized item pool had already been developed and new items were to be added to that item pool. The results suggested that the item characteristic curve method generally performed well. The performance of the fixed common item parameter calibration method and the concurrent calibration method worsened in one of the linking designs where the number of common items was small. The results also suggested that performance was better when the sample size per form and the number of common items were large.

     

Measuring client satisfaction with public education III: group effects in client satisfaction

A contracted research project to evaluate client satisfaction with public education (King and Bond, 2003; Bond and King, 2003) required that the satisfaction of certain groups of clients received particular attention. A number of target groups were specifically identified by the state education department as those requiring separate satisfaction analyses. ConQuest software (Wu, Adams and Wilson, 1997) provided convenient techniques for estimating group mean effects for identified sub-groups of the parent and student samples. This allowed for the analysis of directly comparable satisfaction estimates for groups such as these, as well as for school size, school type, school location and parents according to the year level of the child's school class. Rasch analyses of group mean effects revealed generally, that for students, differences in overall satisfaction levels between identified sub-samples and the whole student sample even if statistically significant, were, at most, substantively marginal. However, for identified groups of parents and caregivers, the results were not so equivocal: one group of indigenous Australians, and parents of children with disabilities showed marked positive group mean effects, while another group of indigenous Australians reported lower satisfaction levels than did the whole parent sample. Moreover, analyses based on groupings of schools according to their relative complexity, appeared to reiterate the finding mentioned en passant in a previous paper (King and Bond, 2003), that client satisfaction decreased as school size increased.     

Coating-thickness measures

Measurement Techniques -     

基于科技创新模块系统和远程仿真系统展开大学生科技创新能力的培养

本文论述了科技刨新程序模块系统和远程仿真系统对大学生科技创新能力的培育模式。依据自动控制专业和计算机专业的科技创新热点课题，建立相应的模块程序文件，借用现成的MATLAB Web Server技术，建立数据挖掘等研究课题的远程仿真系统。     

Domain-based production configuration with constraint satisfaction

Production configuration is well recognised as an effective means of planning production processes for product families. The major challenge of production configuration originates from the handling of the numerous constraints associated with product and process variety. This paper develops a constraint satisfaction approach to facilitate production configuration decisions regarding constraint identification, representation, and evaluation. A domain-based model is formulated to conceptualise the production configuration process, involving inter-connections among multiple domains in conjunction with diverse domain decision variables and constraints. Within the domain framework, production configuration is formulated as a constraint satisfaction problem (CSP), which is solved using constraint heuristic search. Within constraint heuristic search, a decision propagation structure incorporating a connectionist approach is developed to facilitate the exploration of solution spaces. A case study of textile spindle production configuration is elaborated to illustrate the feasibility and potential of the domain-based CSP model for production configuration.     

Bibliometric performance measures

Three different types of bibliometrics — literature bibliometrics, patent bibliometrics, and linkage bibliometric can all be used to address various government performance and results questions. Applications of these three bibliometric types will be described within the framework of Weinberg's internal and external criteria, whether the work being done is good science, efficiently and effectively done, and whether it is important science from a technological viewpoint. Within all bibliometrics the fundamental assumption is that the frequency with which a set of papers or patents is cited is a measure of the impact or influence of the set of papers. The literature bibliometric indicators are counts of publications and citations received in the scientific literature and various derived indicators including such phenomena as cross-sectoral citation, coauthorship and concentration within influential journals. One basic observation of literature bibliometrics, which carries over to patent bibliometrics, is that of highly skewed distributions — with a relatively small number of high-impact patents and papers, and large numbers of patents and papers of minimal impact. The key measure is whether an agency is producing or supporting highly cited papers and patents. The final set of data are in the area of linkage bibliometrics, looking at citations from patents to scientific papers. These are particularly relevant to the external criteria, in that it is quite obvious that institutions and supporting agencies whose papers are highly cited in patents are making measurable contributions to a nation's technological progress.     

测量审核的实施方法及满意度评定

针对在质量计量工作中常用作实验室能力验证的测量审核工作,具体介绍该工作的实施过程,并以测量F1等级砝码的折算质量修正值为实例,详细分析砝码测量审核的数据处理过程,采用En值评定、CD值评定和Z值评定3种方法判定测量结果的满意度,从而验证申请实验室的检测和校准能力,确保质量量值传递的准确性。     

Meshless boundary integral equations with equilibrium satisfaction

A known feature of any mixed interpolation boundary integral equations (BIE)-based methods is that equilibrium is not generally guaranteed in the numerical solution. Here, a complete meshless technique, based on the boundary element-free method (BEFM) with complete equilibrium satisfaction for 2D elastostatic analysis is proposed. The BEFM adopted is a meshless method based on boundary integral equations such as local boundary integral equation (LBIE) method and boundary node method (BNM), differing from them with respect to the integration domain and the approximation scheme.     

Stochastic networks for constraint satisfaction and optimization

Stochastic algorithms for solving constraint satisfaction problems with soft constraints that can be implemented on a parallel distributed network are discussed in a unified framework. The algorithms considered are: the Boltzmann machine, a Learning Automata network for Relaxation Labelling and a formulation of optimization problems based on Markov random field (mrf) models. It is shown that the automata network and themrf formulation can be regarded as generalisations of the Boltzmann machine in different directions.     

Total customer satisfaction as a business strategy

There are two fundamental goals which are universal in business. The first is to grow market share, and the second to grow profits. In order to accomplish these goals, the company must differentiate itself from its competitors, in the customer's view, in one or more of the five following areas: (1) price, (2) delivery, (3) performance, (4) quality, (5) total customer experience. Stressing one area of differentiation to the exclusion of the others will not achieve the goals. For example, in stressing price alone, a company has defined its products as a commodity and as Dev Dion of the Strategic Planning Institute once said, ‘The producers of commodities reap commensurate rewards.’ Similarly, stressing fast delivery of a product of poor quality, or stressing superior quality for a product providing marginally useful performance are both losing strategies. The only strategy I know of which provides equally balanced focus on all five major areas of differentiation is total customer satisfaction, as the fundamental objective of the company. Bob Galvin, when Chairman of Motorola, summed it up by saying, ‘If you take care of the customer better than any of your competition, the business will take care of itself.’ In saying this, however, he meant not only the product, but all of the other ways in which you and the customer interact.     

网络环境下研究生管理新探索

文章分析了目前研究生管理工作中存在的问题,提出了创建研究生网络班级,加强研究生班级建设的新思路,并给出了具体的实现方案.     

On- and off-campus student persistence and academic performance

A study of more than 9000 unit enrolments in an Australian engineering programme found that: (a) the off-campus withdrawal rate was close to twice that for on-campus students; (b) whether a student withdrew or not was highly correlated to their mode of study; (c) the rate of withdrawal was significantly different between the two student groups; (d) the grade distribution for completing students was significantly different between the two groups; (e) the mean final grade was significantly higher for off-campus students; (f) the failure rate for off-campus students was significantly lower; and (g) the overall wastage rate (withdrawn rate plus fail rate) was significantly higher for off-campus students