中国少数民族考生与外国考生HSK成绩的公平性分析

该研究利用项目功能差异(Differential Item Functioning,简称DIF)理论,对HSK考生中不同两个群体——外国人和中国国内的少数民族,进行题目的反应分析。考查HSK的题目是否存在不利于某一群体。具体做法：采用MH和SIBTEST方法检测DIF,利用标准化的离散分析方法和SIBTEST的项目束分析法鉴别DIF的真伪,并寻找造成DIF的原因。由数据分析的结果可知,HSK(初、中等)A卷对对外国考生和中国国内的少数民族考生存在一些有DIF的题目。     

LP方法及其与三种常用DIF检测方法的比较

本研究基于项目反应理论,提出了一种检验力高且犯Ⅰ类错误率小的检测DIF的新方法：LP法（Likelihood Procedure）,且以2PLM下对题目进行DIF检验为例介绍此法。本文通过与MH方法、Lord卡方检验法和Raju面积测量法三种常用的检验DIF的方法比较研究LP法的有效性,同时探讨样本容量、测验长度、目标组和参照组能力分布的差异、DIF值大小等相关因素对LP法有效性可能产生的影响。通过模拟研究,得到以下结论：(1)LP法比MH法及Lord卡方法更灵敏且更稳健;(2) LP法比Raju面积测量法更合理;(3)LP法的检验力随着被试样本容量或DIF值的增大而增大;（4）当参照组与目标组的能力无差异时,LP法在各种条件下的检验力比参照组与目标组的能力有差异时的检验力高;（5）LP法对一致性DIF和非一致性DIF都有良好的检验力,且LP法对一致性DIF的检验力比对非一致性DIF的检验力高。LP法可以简便的扩展并运用到多维度、多级评分项目上。     

认知诊断测验中的项目功能差异检测方法比较

检测项目功能差异(DIF)是认知诊断测验中很重要的问题。首先将逻辑斯蒂克回归法(LR)引入认知诊断测验DIF检测, 然后将LR法与MH法和Wald检验法的DIF检验效果进行比较。在比较中同时考察了匹配变量、DIF种类、DIF大小和受测者人数的影响。结果表明：(1) LR法在认知诊断测验DIF检测中, 检验力较高, 一类错误率较低。(2) LR法在检测认知诊断测验的DIF时, 不受认知诊断方法的影响。(3) LR法可以有效区分一致性DIF和非一致性DIF, 并有较高检验力和较低一类错误率。(4)采用知识状态作为匹配变量, 能够得到较理想的检验力和一类错误率。(5) DIF越大, 受测者人数越多, 统计检验力越高, 但一类错误率不受影响。     

认知诊断框架下多级评分题目的DIF检测方法及其应用

本文对多级计分认知诊断测验的DIF概念进行了界定,并通过模拟实验以及实证研究对四种常见的多级计分DIF检验方法的适用性进行理论以及实践性的探索。研究结果表明：四种方法均能对多级计分认知诊断中的DIF进行有效的检验,且各方法的表现受模型的影响不大;相较于以总分为匹配变量,以KS为匹配变量时更利于DIF的检测;以KS为匹配变量的LDFA方法以及以KS为匹配变量的曼特尔检验方法在检测DIF题目时有着最高的检验力。     

OR法在DIF检验中的应用——以英语学业能力测验为例

本文将比值比方法（odds ratios method, OR）这一DIF检验方法应用到某英语测验的DIF检验中,介绍OR法进行DIF检验的完整流程,并将其检验结果与应用较为广泛的Waldχ2检验和似然比检验（likelihood ratio test, LRT）的检验结果进行比较,以进一步验证OR法在实证研究中的适用性。研究结果显示,OR法与LRT法结果差异较小且OR法步骤更简便,说明OR法与LRT法在DIF检验中的表现相似,LRT法适用于实证研究中,因此OR法同样适用于实证研究的DIF检验。     

IRT_Δb法和修正LR法对矩阵取样DIF检验的有效性

矩阵取样测验包含多个题册,单个题册的总分不能直接作为匹配变量用于 DIF 检测。本研究首先基于模拟数据,同时采用 I RT_Δb法,以及用 I RT模型估计的考生能力作为匹配变量修订后的 L R法对矩阵取样测验进行DIF检测,分析二者进行DIF检测的有效性及其相关影响因素;并根据已有的LR法DIF判断标准划定出I RT_Δb法分类标准;最后使用实证数据加以验证。结果显示：矩阵取样测验中, I RT_Δb法和修正LR法均能较好地区分DIF量不同的题目;样本量、题册中DIF题目的比例和考生群体间真实能力的差异对两种方法的检验力、犯I类错误的概率和分类结果都有较大影响。     

变通的题组项目功能差异检验方法在篇章阅读测验中的应用

篇章形式的阅读测验在语文学科考试与语言能力测试中占有越来越重要的地位。篇章阅读测验是一种典型的题组测验, 因此需要采用能够处理题组效应的统计方法进行分析。在进行项目功能差异(DIF)检验时, 也需要采用与之匹配的DIF检验方法。目前能够处理题组效应的DIF检验方法主要包括变通的题组DIF检验方法和基于题组反应模型的DIF检验方法, 基于题组反应模型的DIF检验方法由于实现过程繁琐, 目前只停留在理论探讨阶段。本研究将变通的题组DIF检验方法及其效应值指标引入篇章阅读测验的DIF检验中, 能够解决篇章阅读测验中DIF检验与测量的问题, 效应值指标能够为如何处理有DIF效应的题组项目提供重要依据。本研究首先选用非题组DIF检验方法与变通的题组DIF检验方法对一份试卷进行DIF检验, 两种方法的比较结果体现了进行题组DIF检验的必要性与优越性, 然后选用变通的题组DIF检验方法中有代表性的四种方法对某阅读成就测验进行题组DIF检验。研究结果表明, 在篇章阅读测验中, 能够处理题组效应的DIF检验方法较传统的DIF检验方法具有较大的优越性。     

题组项目功能差异（DIF）检验方法的应用探索

篇章形式的阅读测验是一种典型的题组测验,在进行项目功能差异（DIF）检验时需要采用与之匹配的DIF检验方法.基于题组反应模型的DIF检验方法是真正能够处理题组效应的DIF检验方法,能够提供题组中每个项目的DIF效应测量,是题组DIF检验方法中较有理论优势的一种,主要使用的方法是Rasch题组DIF检验方法.该研究将Rasch题组DIF检验方法引入篇章阅读测验的DIF检验中,对某阅读成就测验进行题组DIF检验,结果显示,该测验在内容维度和能力维度的部分子维度上出现了具有显著DIF效应的项目,研究从测验公平的角度对该测验的进一步修改及编制提出了一定的建议.研究中进一步将Rasch题组DIF检验方法与基于传统Rasch模型的DIF检验方法以及变通的题组DIF检验方法的结果进行比较,研究结果体现了进行题组DIF检验的必要性与优越性.研究结果表明,在篇章阅读测验中,能够真正处理题组效应的题组DIF检验方法更加具有理论优势且对于阅读测验的编制与质量的提高具有更重要的意义.     

经济法试题DIF的参数法检测研究

该研究基于项目反应理论的Samejima等级反应模型(GRM),在MULTILOG软件支持下,应用参数检测方法,对某年度全国性资格考试的某科目试卷中经济法部分的21个项目做了DIF检测分析。结果如下:存在性别DIF的项目一个,存在民族DIF的项目四个,存在工作性质DIF的项目一个。其中项目68在民族层面上表现为一致性DIF,项目64既存在民族DIF又存在工作性质DIF。通过对项目统计量、反应曲线的分析和专家的讨论,文章最后还分析了产生这些DIF的几个可能的原因。     

运用均数与协方差结构模型侦查项目功能差异

阐释了运用多组均数与协方差结构(MACS)模型侦查多级反应项目的一致性与非一致性项目功能差异(DIF)的原理与程序, 以道德自我概念量表DIF的侦查进行示例, 并对该方法进行了评价。与项目反应理论比照, MACS采用系统的、迭代的方式利用修正指数来侦查DIF, 并提供多个拟合指数协同评价模型拟合;与标准验证性因素分析相较, MACS不仅能侦查非一致性DIF, 而且能侦查一致性DIF。运用MACS侦查DIF是一种值得推荐的方法。     

A new procedure for detection of crossing DIF

The purpose of this paper is to present a hypothesis testing and estimation procedure, Crossing SIBTEST, for detecting crossing DIF. Crossing DIF exists when the difference in the probabilities of a correct answer for the two examinee groups changes signs as ability level is varied. In item response theory terms, crossing DIF is indicated by two crossing item characteristic curves. Our new procedure, denoted as Crossing SIBTEST, first estimates the matching subtest score at which crossing occurs using least squares regression analysis. A Crossing SIBTEST statistic then is used to test the hypothesis of crossing DIF. The performance of Crossing SIBTEST is evaluated in this study.This research was partially supported by a grant from the Law School Admission Council and by National Science Foundation Mathematics Grant NSF-DMS-94-04327. The research reported here is collaborative in every respect and the order of authorship is alphabetical. The authors thank Jeff Douglas and Louis Roussos for their useful comments and discussions.     

Improving the Crossing-SIBTEST Statistic for Detecting Non-uniform DIF

This paper demonstrates that, after applying a simple modification to Li and Stout’s (Psychometrika 61(4):647–677, 1996) CSIBTEST statistic, an improved variant of the statistic could be realized. It is shown that this modified version of CSIBTEST has a more direct association with the SIBTEST statistic presented by Shealy and Stout (Psychometrika 58(2):159–194, 1993). In particular, the asymptotic sampling distributions and general interpretation of the effect size estimates are the same for SIBTEST and the new CSIBTEST. Given the more natural connection to SIBTEST, it is shown that Li and Stout’s hypothesis testing approach is insufficient for CSIBTEST; thus, an improved hypothesis testing procedure is required. Based on the presented arguments, a new chi-squared-based hypothesis testing approach is proposed for the modified CSIBTEST statistic. Positive results from a modest Monte Carlo simulation study strongly suggest the original CSIBTEST procedure and randomization hypothesis testing approach should be replaced by the modified statistic and hypothesis testing method.     

A model-based standardization approach that separates true bias/DIF from group ability differences and detects test bias/DTF as well as item bias/DIF

A model-based modification (SIBTEST) of the standardization index based upon a multidimensional IRT bias modeling approach is presented that detects and estimates DIF or item bias simultaneously for several items. A distinction between DIF and bias is proposed. SIBTEST detects bias/DIF without the usual Type 1 error inflation due to group target ability differences. In simulations, SIBTEST performs comparably to Mantel-Haenszel for the one item case. SIBTEST investigates bias/DIF for several items at the test score level (multiple item DIF called differential test functioning: DTF), thereby allowing the study of test bias/DIF, in particular bias/DIF amplification or cancellation and the cognitive bases for bias/DIF.This research was partially supported by Office of Naval Research Cognitive and Neural Sciences Grant N0014-90-J-1940, 4421-548 and National Science Foundation Mathematics Grant NSF-DMS-91-01436. The research reported here is collaborative in every respect and the order of authorship is alphabetical. The assistance of Hsin-hung Li and Louis Roussos in conducting the simulation studies was of great help. Discussions with Terry Ackerman, Paul Holland, and Louis Roussos were very helpful.     

Model-Based Measures for Detecting and Quantifying Response Bias

This paper proposes a model-based family of detection and quantification statistics to evaluate response bias in item bundles of any size. Compensatory (CDRF) and non-compensatory (NCDRF) response bias measures are proposed, along with their sample realizations and large-sample variability when models are fitted using multiple-group estimation. Based on the underlying connection to item response theory estimation methodology, it is argued that these new statistics provide a powerful and flexible approach to studying response bias for categorical response data over and above methods that have previously appeared in the literature. To evaluate their practical utility, CDRF and NCDRF are compared to the closely related SIBTEST family of statistics and likelihood-based detection methods through a series of Monte Carlo simulations. Results indicate that the new statistics are more optimal effect size estimates of marginal response bias than the SIBTEST family, are competitive with a selection of likelihood-based methods when studying item-level bias, and are the most optimal when studying differential bundle and test bias.     

Using the teaching interaction procedure to train interventionists to implement the Cool versus Not CoolTM procedure

The teaching interaction procedure is a behavior analytic procedure that has been used to target the development of social skills. The teaching interaction procedure consists of labeling the target skill, providing a meaningful rationale, describing the steps of the target skill, modeling the skill, role‐play, and providing feedback throughout the interaction. Although the teaching interaction procedure has been used to teach a variety of social skills for individuals diagnosed with autism spectrum disorder (ASD), it has only been used to train staff in two studies. The purpose of this study was to evaluate the use of the teaching interaction procedure to teach three interventionists to implement the Cool versus Not Cool? procedure to target the development of social skills for children diagnosed with ASD. The results of a multiple baseline design demonstrated that the teaching interaction procedure was effective for all three interventionists. Results of the child participants' skill acquisition are also provided.     

The operant conditioning of response variability: Free-operant versus discrete-response procedures

The operant conditioning of response variability under free-operant and discrete-response procedures was investigated. Two pigeons received food only if their pattern of four pecks on two response keys differed from the patterns emitted on the two immediately preceding trials. Under the free-operant procedure, the keys remained illuminated and operative throughout each trial. There was little variability in the response patterns that resulted, and the pigeons received fewer than one third of the available reinforcers. Under the discrete-response procedure, a brief timeout period followed each response. Variability increased under this procedure, and the pigeons obtained three fourths of the available reinforcers. Previous successes and failures to produce response variability may have been due to the use or failure to use, respectively, a discrete-response procedure. Respondent effects inherent in the free-operant procedure may encourage the development of response stereotypy and, in turn, prevent the development of response variability.     

The elimination‐plus lineup: Testing a modified lineup procedure with confidence

The present study examined whether a modified form of a preidentification confidence rating would provide evidence of a suspect's guilt in addition to the identification decision confidence. Participants (N  = 241) viewed a videotaped mock crime and were presented with a target‐present or target‐absent simultaneous, sequential, elimination, or elimination‐plus lineup procedure; both elimination procedures required 2 separate judgments from the witness (i.e., relative and absolute). The elimination‐plus procedure was identical to that of the elimination procedure with the addition of the confidence rating in between judgment 1 and judgment 2. Confidence after judgment 1, confidence after judgment 2, and the average of the 2 confidence ratings with the elimination‐plus procedure significantly predicted accuracy for choosers. Given that confidence has been recognised by the Supreme Court of the United States, these results shed light on a novel way of utilising confidence in the investigative process.     

关于高级内隐认知研究方法的一点浅见

本文对加工分离程序应用于高级内隐认知加工的可能性作了论证,并以内隐学习研究为例,进行了实验检验,证明其切实可行.     

儿童青少年返回抑制发展的实验研究

采用返回抑制线索——靶子模式,比较了单线索和双线索条件下儿童返回抑制的发展变化。选取了4组被试,6岁、9岁、12岁和17岁各20名。结果显示:(1)儿童返回抑制在单线索条件下出现的晚,而在双线索条件下出现的早;(2)返回抑制出现的时间进程随年龄的增长而逐渐显现,年龄对返回抑制有重要影响;(3)儿童返回抑制发展的关键期可能是在12岁左右。