Kernel smoothing approaches to nonparametric item characteristic curve estimation

The option characteristic curve, the relation between ability and probability of choosing a particular option for a test item, can be estimated by nonparametric smoothing techniques. What is smoothed is the relation between some function of estimated examinee ability rankings and the binary variable indicating whether or not the option was chosen. This paper explores the use of kernel smoothing, which is particularly well suited to this application. Examples show that, with some help from the fast Fourier transform, estimates can be computed about 500 times as rapidly as when using commonly used parametric approaches such as maximum marginal likelihood estimation using the three-parameter logistic distribution. Simulations suggest that there is no loss of efficiency even when the population curves are three-parameter logistic. The approach lends itself to several interesting extensions.The author wishes to acknowledge the support of the National Sciences and Engineering Research Council of Canada through grant A320 and the support of Educational Testing Service during his leave there.     

Maximum likelihood estimation of polyserial correlations

This paper considers a multivariate normal model with one of the component variables observable only in polytomous form. The maximum likelihood approach is used for estimation of the parameters in the model. The Newton-Raphson algorithm is implemented to obtain the solution of the problem. Examples based on real and simulated data are reported.The research of the first author was supported in part by a research grant (DA01070) from the US Public Health Service. We are indebted to the referees and the editor for some very valuable comments and suggestions.     

The asymptotic posterior normality of the latent trait for polytomous IRT models

Chang and Stout (1993) presented a derivation of the asymptotic posterior normality of the latent trait given examinee responses under nonrestrictive nonparametric assumptions for dichotomous IRT models. This paper presents an extention of their results to polytomous IRT models in a fairly straightforward manner. In addition, a global information function is defined, and the relationship between the global information function and the currently used information functions is discussed. An information index that combines both the global and local information is proposed for adaptive testing applications.This research was partially supported by Educational Testing Service Allocation Project No. 79424. The author wishes to thank Charles Davis, Xuming He, Frank Jenkins, Spence Swinton, William Stout, Ming-Mai Wang, and Zhiliang Ying for their helpful comments and discussions. The author particularly wishes to thank the Editor, Shizuhiko Nishisato, the Associate Editor, and three anonymous reviewers for their thoroughness and thoughtful suggestions.     

相信智力不变是否也认为个性难改?——个人属性内隐观的普遍性

动机理论的认知心理学派认为 ,学生对智力、个性等个人属性 ,是否先天固有不可改变的主观想法 ,将直接影响他们的学习和行为表现。其影响的范围 ,将取决于这类主观想法是否具有普遍性。比如 ,有些学生认为智力是父母遗传的 ,很难改变 ,这些学生会否同样认为个性、道德等 ,也是父母遗传 ,亦难改变 ?该研究希望了解是否有一主导思想 ,影响学生对智力、个性等不同个人属性 ,是否先天不变的整体看法。被试为中国长春市高中一年级的学生 ,总计 5 5 5人。研究采用问卷调查 ,通过比较多个结构方程模型 ,结果较倾向支持学生对个性、智力等五项个人属性有共通一致的内隐观     

Dominance Measuring Method Performance under Incomplete Information about Weights

In multi‐attribute utility theory, it is often not easy to elicit precise values for the scaling weights representing the relative importance of criteria. A very widespread approach is to gather incomplete information. A recent approach for dealing with such situations is to use information about each alternative's intensity of dominance, known as dominance measuring methods. Different dominance measuring methods have been proposed, and simulation studies have been carried out to compare these methods with each other and with other approaches but only when ordinal information about weights is available. In this paper, we use Monte Carlo simulation techniques to analyse the performance of and adapt such methods to deal with weight intervals, weights fitting independent normal probability distributions or weights represented by fuzzy numbers. Moreover, dominance measuring method performance is also compared with a widely used methodology dealing with incomplete information on weights, the stochastic multicriteria acceptability analysis (SMAA). SMAA is based on exploring the weight space to describe the evaluations that would make each alternative the preferred one. Copyright © 2012 John Wiley & Sons, Ltd.     

Downsizing and Supersizing: How Changes in Product Attributes Influence Consumer Preferences

This paper investigates how changing the value of one attribute while keeping other attributes constant influences consumers' judgments and behaviors. We find that in two options, a proportionally equal change in one attribute tilts people's preference toward the option with higher (or lower) absolute magnitude of change when the change is desirable (or undesirable). We propose that when individuals face an attribute change, they use a deliberative and effortful response, known as System 2, to detect the change. However, they rely less on this system to evaluate the changed options. Instead, a more automatic System 1 processing influences their decision by making them apply the bigger‐is‐better heuristic (bigger‐is‐worse for an undesirable change) to prefer the option with the highest (lowest) absolute magnitude of change. Six studies demonstrate this phenomenon in both lab and real settings and support our hypothesis. Copyright © 2013 John Wiley & Sons, Ltd.     

Spinoza's Definition Of Attribute: An Interpretation

Since it has generally been accepted that to Spinoza attributes are real features of substance, the interpretation of his attribute definition has become a notorious problem. The reason is that interpreters have failed to see that the definition formulates a purely epistemological account of the state of affairs. The article presents and justifies such an interpretation. It will be shown that the definition in spite of its epistemological character implies a real ontological definition, which specifies the critical features of an attribute. As to the reason why Spinoza has stated the definition in an ‘indirect way’, it is shown that it is likely that he has done so in order to have a more efficient, a more unambiguous and a more elegant definition. The relevance of the new interpretation is not only that it provides us with an interpretable, transparent attribute definition, but it also contributes to the establishment of a coherent picture of Spinoza’s metaphysics around this definition.     

现代针灸学研究应当警惕被文化绑架

针灸学的文化属性由其漫长的历史积淀特质所决定,针灸学的科学属性由其在现实中治疗疾病的有效性及其机制的探索过程所决定.针灸学的文化属性与科学属性犹如硬币的正反两面永远无法分离,但无法实现同一个角度的双面认识.不能以其文化属性而排斥科学属性,不能利用文化角度的认识方法和认识结果取代科学角度的探索方法和探索结果,反之亦然.文化的针灸可以努力固守,以保个性的纯洁与永恒;但科学的针灸需要不断发展,以超越个性文化而走向科学大同.现代针灸学研究应当警惕被文化绑架.     

特征框架效应的心理机制与影响因素

特征框架效应是指当分别以积极框架和消极框架来描述给定情境中某一事物或事件的关键特征时, 一般情况下人们更偏好以积极框架来描述其关键特征的事物或事件的现象。特征框架效应广泛的存在于消费、医学及政治等领域。目前, 它的解释机制主要包括效价加工的认知机制、参照依赖、查询理论以及认知神经机制。它的影响因素主要包括经验、人格特质、计算能力以及认知闭合需要等。未来的研究应该从深入探索特征框架效应的产生根源和影响因素, 拓展其应用研究, 深入探索偏好消极框架下的特征框架效应以及探讨该现象与其它现象之间的关系等五方面展开。     

计算机化自适应测验在认知诊断中的应用

作为认知诊断与计算机化自适应测验相结合的产物, 认知诊断计算机化自适应测验(Cognitive Diagnostic Computerized Adaptive Testing, CD-CAT)是对被试知识状态的自适应。它既有传统CAT所面临的普遍性问题, 也有在认知诊断中遇到的特殊问题：由于认知诊断中涉及属性这一概念, CD-CAT与传统CAT有很大的差别。本文紧紧围绕属性引起的差异, 分别从认知诊断模型、题库建设、起始规则、选题策略、被试知识状态估计和终止规则等几部分详细介绍CD-CAT的研究进展和存在的问题。