High-dimensional maximum marginal likelihood item factor analysis by adaptive quadrature

Although the Bock–Aitkin likelihood-based estimation method for factor analysis of dichotomous item response data has important advantages over classical analysis of item tetrachoric correlations, a serious limitation of the method is its reliance on fixed-point Gauss-Hermite (G-H) quadrature in the solution of the likelihood equations and likelihood-ratio tests. When the number of latent dimensions is large, computational considerations require that the number of quadrature points per dimension be few. But with large numbers of items, the dispersion of the likelihood, given the response pattern, becomes so small that the likelihood cannot be accurately evaluated with the sparse fixed points in the latent space. In this paper, we demonstrate that substantial improvement in accuracy can be obtained by adapting the quadrature points to the location and dispersion of the likelihood surfaces corresponding to each distinct pattern in the data. In particular, we show that adaptive G-H quadrature, combined with mean and covariance adjustments at each iteration of an EM algorithm, produces an accurate fast-converging solution with as few as two points per dimension. Evaluations of this method with simulated data are shown to yield accurate recovery of the generating factor loadings for models of upto eight dimensions. Unlike an earlier application of adaptive Gibbs sampling to this problem by Meng and Schilling, the simulations also confirm the validity of the present method in calculating likelihood-ratio chi-square statistics for determining the number of factors required in the model. Finally, we apply the method to a sample of real data from a test of teacher qualifications.     

Stereotype Threat in Men on a Test of Social Sensitivity

This study provides evidence of stereotype threat in men on a test of a feminine ability called social sensitivity, that is, the ability to decode nonverbal cues. Men who were told that the test assessed social sensitivity and produced better scores for women than men performed worse on the test than did men who were told that the test assessed information processing. Because social sensitivity can be an automatic skill and stereotype threat uses mental capacity, this effect was moderated by self-reported strategy usage. Mens performance worsened in the threat condition only when they reported more deliberative and less intuitive strategies for decoding nonverbal cues.     

汉语转折复句的命题表征项目互换效应研究

采用句子一图画验证任务(sentence-picture verification task)探讨了汉语转折复句的命题表征项目互换效应。结果表明,汉语倒装转折复句的项目表达顺序为“(但是)B→虽然A”,命题表征中项目存在着互换的倾向,所形成的命题表征为“虽然A→但是B”。本研究结果初步表明,读者理解汉语转折复句可能是一个按照“虽然A(事实让步)→但是B(转折)”固定方向进行系列认知加工的过程。     

汉语因果复句的心理表征项目互换效应研究

采用句子-图画验证任务(sentence picture verification task)探讨了汉语因果复句的心理表征项目互换效应。结果表明,汉语因果复句的项目表达顺序为"结果→原因"时,所形成的心理表征中项目发生互换,其结果为"原因→结果"。本研究结果初步表明,读者理解汉语因果复句是一个按照"原因→结果"固定方向进行系列加工的认知过程。     

Treatment efficacy of noncontingent reinforcement during brief and extended application

We evaluated the long-term therapeutic effects of noncontingent reinforcement (NCR). In Experiment 1, NCR effects were examined with 2 participants' arbitrary responses; in Experiment 2, NCR was used as treatment with 3 participants whose self-injurious behavior (SIB) was maintained by automatic reinforcement. In both experiments, NCR consisted of continuous access to a highly preferred leisure item and was implemented initially during 10-min and later during 120-min sessions. Varied reinforcers (leisure items) were subsequently introduced during 120-min sessions to determine if treatment effects might be extended. Finally (Experiment 2 only), NCR was implemented throughout the day in participants' homes. Results of Experiments 1 and 2 showed that reinforcers obtained through object manipulation can compete with those obtained automatically by engaging in SIB during brief NCR sessions. However, data from the 120-min sessions indicated that satiation to a specific leisure item might occur over periods of time more typical of those during which treatment would be implemented. Access to a variety of highly preferred leisure items extended the effectiveness of NCR for some individuals. When NCR was implemented throughout the day (Experiment 2), therapeutic effects were shown to be maintained for up to 1 year.     

The Emerging Gender Gap: Cultural and Economic Conservatism in the Netherlands 1970–1992

Research on gender differences in political alignments and cultural orientations in the past decades reveals a large value change in women relative to that in men, indicating that women might recently have become less conservative than men, whereas women used to be more conservative in many respects. In this article this possible reversal in the gender gap in recent decades is analyzed. Recent research has demonstrated that in the Netherlands women are presently less conservative than men. This lower level of conservatism in Dutch women is apparent with respect to both economic and cultural issues. It is investigated whether these gender differences are due to a reversal in the gender gap in the Netherlands and if so, how this emerging gender gap can be explained. Three explanations are hypothesized: one in terms of the characteristics of the youngest generations (the gender-cohort model), the second in terms of growing structural equality between women and men in general (the situational/structural model), and a specification of the second model, in which differential effects of structural factors for women and men are presumed to have their effect (the gender-interaction model). Neither of the three tested models was in itself able to fully explain the results. The gender gap can partly be explained by growing structural equality between women and men, partly by the fact that the gender gap is largest in the youngest generations (economic conservatism), and partly by the fact that the gender gap is largest between groups of "independent" women and their male counterparts. Possible additional determinants are also discussed.     

An item response model with internal restrictions on item difficulty

An IRT model based on the Rasch model is proposed for composite tasks, that is, tasks that are decomposed into subtasks of different kinds. There is one subtask for each component that is discerned in the composite tasks. A component is a generic kind of subtask of which the subtasks resulting from the decomposition are specific instantiations with respect to the particular composite tasks under study. The proposed model constrains the difficulties of the composite tasks to be linear combinations of the difficulties of the corresponding subtask items, which are estimated together with the weights used in the linear combinations, one weight for each kind of subtask. Although the model does not belong to the exponential family, its parameters can be estimated using conditional maximum likelihood estimation. The approach is demonstrated with an application to spelling tasks. We thank Eric Maris for his helpful comments.     

Nonparametric polytomous IRT models for invariant item ordering, with results for parametric models

It is often considered desirable to have the same ordering of the items by difficulty across different levels of the trait or ability. Such an ordering is an invariant item ordering (IIO). An IIO facilitates the interpretation of test results. For dichotomously scored items, earlier research surveyed the theory and methods of an invariant ordering in a nonparametric IRT context. Here the focus is on polytomously scored items, and both nonparametric and parametric IRT models are considered.The absence of the IIO property in twononparametric polytomous IRT models is discussed, and two nonparametric models are discussed that imply an IIO. A method is proposed that can be used to investigate whether empirical data imply an IIO. Furthermore, only twoparametric polytomous IRT models are found to imply an IIO. These are the rating scale model (Andrich, 1978) and a restricted rating scale version of the graded response model (Muraki, 1990). Well-known models, such as the partial credit model (Masters, 1982) and the graded response model (Samejima, 1969), do no imply an IIO.     

The Analysis of Intervention Change in Children and Families: Methodological and Conceptual Issues Embedded in Intervention Studies

This article provides an overview of methodological and conceptual issues underlying the assessment of change during psychotherapy with children and families. Three central considerations are discussed: (1) What changes do we measure? (2) When do we measure change? (3) How do we measure change? The difficulties with the traditional methods of assessing change are highlighted, and suggestions for a new paradigm that calls for expansion of the nomological network relevant to the analysis of change, as well as the inclusion of more assessment points and more reliable and valid measures of the change process, are presented. Illustrations of key points are provided from the Adolescent Transitions Program, a theoretically based intervention program targeting high-risk youth.     

画人智力测验评分项目的再确定

该研究参照国内外已有的画人测验材料 ,并在以往使用绘人智能测验的基础上 ,重新设计 ,提出了一份包含 80个评分项目的画人评分标准。新标准首先在课题组内试用修改 ,然后又用于 9名标准评分员的培训 ,最后运用总计 2 5 8名 ,年龄为 6～ 1 2岁的小学儿童作预试 ,进行系统的项目分析。在上述过程中 ,对项目进行反复推敲删改 ,最终形成了一份供制订画人智力测验常模用的画人评分标准。该标准分有无、细节、比例、奖励四个维度 ,按身体部位分成头、头发、眼、耳、鼻、口、颈、躯干、上肢、手、下肢、脚以及连接和服饰共十四个大类 ,每大类包含 4～ 8个评分点 ,总计 75个评分点。