结构方程建模中的题目打包策略

结构方程建模中题目打包法的优缺点包括：指标数据质量变好、模型拟合程度提高; 估计偏差不大, 可校正; 估计稳定, 但降低了敏感性与可证伪性。打包法的前提条件是单维、同质, 适合结构模型分析, 不适合测量模型分析。对于单维测验, 给出了一个打包流程。对于通常的多个子量表(多维结构)测验, 推荐在子量表内打包, 每个子量表打包成1个指标或者3个指标, 用于结构方程建模。     

基于混合模型（Mixed-CDMs）视角的CD-CAT及其应用研究

传统CD-CAT通常选择一个认知诊断模型（cognitive diagnosis model, CDM）标定题库参数,但在实际应用中一个CDM很难完全拟合题库中所有的题目。G-DINA模型是一般化的饱和模型,可以通过Wald统计量检验在题目水平上,比较简约模型（DINA、DINO、ACDM、LLM和RRUM）是否能够代替饱和模型（G-DINA）,并为每个题目选择一个相对最优的CDM,从而充分发挥各个CDM的优势,从而在一个题库中有的题目采用简约CDM,而有的题目采用饱和CDM,本文把这种思路称为混合模型（Mixed-CDMs）思路。基于此,本文探讨了基于混合模型的CD-CAT,并通过两个模拟研究及其应用研究验证了该方法的效果。研究结果表明基于混合模型建立的CD-CAT具有理想的效果,从而为CD-CAT在实际使用中提供了新思路和新方法。     

Profile-likelihood Confidence Intervals in Item Response Theory Models

Confidence intervals (CIs) are fundamental inferential devices which quantify the sampling variability of parameter estimates. In item response theory, CIs have been primarily obtained from large-sample Wald-type approaches based on standard error estimates, derived from the observed or expected information matrix, after parameters have been estimated via maximum likelihood. An alternative approach to constructing CIs is to quantify sampling variability directly from the likelihood function with a technique known as profile-likelihood confidence intervals (PL CIs). In this article, we introduce PL CIs for item response theory models, compare PL CIs to classical large-sample Wald-type CIs, and demonstrate important distinctions among these CIs. CIs are then constructed for parameters directly estimated in the specified model and for transformed parameters which are often obtained post-estimation. Monte Carlo simulation results suggest that PL CIs perform consistently better than Wald-type CIs for both non-transformed and transformed parameters.     

Item Response Theory Analyses of the Parent and Teacher Ratings of the DSM-IV ADHD Rating Scale

The graded response model (GRM), which is based on item response theory (IRT), was used to evaluate the psychometric properties of the inattention and hyperactivity/impulsivity symptoms in an ADHD rating scale. To accomplish this, parents and teachers completed the DSM-IV ADHD Rating Scale (DARS; Gomez et al., Journal of Child Psychology and Psychiatry, 40, 265–274, 1999) for a group of 1,475 primary school-aged children. The results for the discrimination parameters showed that all symptoms for both groups of respondents were generally good for discriminating their respective latent traits. For virtually all symptoms, their threshold values showed moderate to large increases in the level of the latent trait at each subsequent response dichotomy, with the symptoms being especially good at representing the appropriate traits from mean to moderately high trait levels. The item information function values for most symptoms indicated reasonable reliability from, approximately, the mean trait levels to moderately high trait levels. These findings indicate good psychometric properties for the parent and teacher ratings of the DARS. The implications of the findings for the use of the DARS and other similar scales are discussed.     

The development of the Children's Empathic Attitudes Questionnaire using classical and Rasch analyses

Empathic responding is implicated in antisocial behaviors such as bullying, sexual offending, and violent crime. Identifying children and adolescents at risk for antisocial behavior and evaluating interventions designed to address problem behaviors require valid and reliable measures. Definitional controversies and limited measurement models have hindered measurement. This study describes the development and analysis of the Children's Empathic Attitudes Questionnaire (CEAQ) using both classical and modern techniques. Rasch analyses provided probabilistic results over large item and person groups, enabling meaningful inferences from patterns of responses at the construct level. Analyses of fifth through seventh graders' responses to the final version of the CEAQ provide support for its reliability, validity, and functionality. Four meaningful item clusters were identified, each reflecting more cognitively advanced empathic attitudes. These analyses suggest that the CEAQ provides a theoretically sound, hierarchically meaningful measure of empathic attitudes that will be useful in identification and intervention with children and adolescents at risk for antisocial behavior.     

推理心理研究中的逻辑加工与非逻辑加工评析

本文对西方心理学研究中有关推理心理学争论的两个热点问题之一：逻辑推理与非逻辑推理之争的发展线索和相互关系等问题进行了评述,指出了这两种理论争论中未能注意到的三个问题,并对试图解决这三个问题的“知识和试题双重结构模型”作了简要介绍。     

等级反应模型项目特征曲线法等值研究

主、客观题并用的测验建项目反应理论题库需作多级模型项目参数等值,本研究推演了等级反应模型下项目特征曲线等值方法并在实际等值试验中获得成功.     

Spontaneous number representation in mosquitofish

While there is convincing evidence that preverbal human infants and non-human primates can spontaneously represent number, considerable debate surrounds the possibility that such capacity is also present in other animals. Fish show a remarkable ability to discriminate between different numbers of social companions. Previous work has demonstrated that in fish the same set of signature limits that characterize non-verbal numerical systems in primates is present but yet to provide any demonstration that fish can really represent number rather than basing their discrimination on continuous attributes that co-vary with number. In the present work, using the method of ‘item by item’ presentation, we provide the first evidence that fish are capable of selecting the larger group of social companions relying exclusively on numerical information. In our tests subjects could choose between one large and one small group of companions when permitted to see only one fish at a time. Fish were successful when both small (3 vs. 2) and large numbers (8 vs. 4) were involved and their performance was not affected by the density of the fish or by the overall space occupied by the group.     

项目功能差异在跨文化人格问卷分析中的应用

利用IRT的等级模型调查了中日两组被试关于SHIBA简易人格量表中“环境敏感性”的项目功能差异(DIF)的现状。研究发现：（1）量表中DIF的项目比例大(3/4);（2）DIF与项目内容、阈值有关而与区分度大小关系不大;（3）DIF项目间的日方特征曲线较之中方有较强的整合性。该研究利用DIF研究结果对跨文化的人格比较作了新尝试。最后提出了关于深化DIF研究的新课题     

应用项目反应理论对《中国士兵人格问卷》的项目分析

采用项目反应理论（IRT）对《中国士兵人格问卷》进行项目分析。计算机呈现中国士兵人格问卷（CSPQ）对100,523名适龄男性青年进行测验,随机抽取2676名任一维度标准分均低于70的定为合格组;将任一维度大于70分并经专业人员访谈不合格的274名定为不合格组;从精神病院抽取男性年龄相当的221名缓解期精神分裂症患者定为精神病组,并完成CSPQ测验。运用基于IRT的双参数Logistic模型进行分析;结果发现,区分度参数超过区间(0.30,4.00)的条目删除前后,被试的能力值与标准分均存在显著相关;精神病组的测验分数经IRT分析,图形曲线与不合格组有高度吻合。研究结果说明,在测验精度基本相同的条件下,应用IRT可以减少施测条目,提高测验效率,可在一定程度上更精确地区分被试的特质水平