Current Location:home > Browse

Institution

1. chinaXiv:202009.00058 [pdf]

变分推断应用于教育测量模型

代立扬
Subjects: Psychology >> Psychological Measurement

变分推断常用于机器学习,是一种仅需编写少量代码便能实现计算速度较快的参数估计算法。研究展示了黑盒变分推断和均摊变分推断在教育测量模型上的应用,开发了可生成任意方差协方差矩阵的潜变量网络、可作为先验分布的神经相关矩阵,基于sigmoid或softmax的属性掌握模式网络等,实验结果显示变分推断在项目反应理论和部分DINA模型上的参数估计性能达到了顶尖水准。研究表明,变分推断能极大的帮助研究人员开发新的教育测量模型,也较适于普通用户在应用场景使用。

submitted time 2020-12-26 Hits2753Downloads592 Comment 0

2. chinaXiv:202012.00013 [pdf]

Assessing two separate dimensions of interpersonal trust: Other-focused trust and propensity to trust

张明
Subjects: Psychology >> Psychological Measurement

One’s propensity to trust others and others’ trustworthiness are two important aspects of interpersonal trust. Both theory and research suggest that it is possible to distinguish between an individual’s propensity to trust (one’s ‘trustingness’ or the extent to which one feels able to trust others) and their other-focused trust (the extent to which one feels that others are worthy of our trust). However, there is as yet no measure that distinguishes between these two components of trust. In three studies, we examined the psychometrics of a proposed two-dimensional measure of trust that encompasses propensity to trust and other-focused trust components. To test discriminant validity, we also administered measures of personality, personal self-esteem, social capital, propensity to like people, perceived social support, as well as general and personal beliefs in a just world. Factor analyses supported the proposed two-factor model for the new trust measure. Further analyses supported the difference between these measures.

submitted time 2020-12-03 Hits1981Downloads317 Comment 0

3. chinaXiv:202010.00072 [pdf]

基于游戏的心理测评:概念,范式及实践

徐俊怡; 李中权
Subjects: Psychology >> Psychological Measurement

基于游戏的心理测评是指通过游戏或游戏化的活动,对一个人的能力、人格等心理特性和行为进行量化测评。早期主要以评估教育、训练效果为目的而后发展成对心理特性的测评,基于游戏的测评作为一项新技术在测评形式、测评过程和测评结果上均具有优势。目前基于游戏的测评形成了以证据中心设计为基础的范式,用于指导建立测评工具并开展实证研究,在测评个体认知能力和非认知能力方面均有实践。然而当前该技术仍处于起步阶段,未来研究可以在任务设计、结果分析及实践应用方面进一步拓展深入。

submitted time 2020-10-26 Hits673Downloads395 Comment 0

4. chinaXiv:202009.00001 [pdf]

基于基尼指数的双目标CD-CAT选题策略

罗芬; 王晓庆; 蔡艳; 涂冬波
Subjects: Psychology >> Psychological Measurement

双目标CD-CAT的测验结果既可用于形成性评估也可用于终结性评估。基尼指数可度量随机变量的不确定性程度,值越小则随机变量的不确定程度越低。本文用基尼指数度量被试知识状态类别以及能力估计置信区间后验概率的变化,提出基于基尼指数的选题策略。Monte Carlo实验表明与已有的选题策略相比,新策略的知识状态分类精度和能力估计精度都较高,同时能有效兼顾题库利用均匀性,并能快速实时响应,且受认知诊断模型和被试知识状态分布的影响较小,可用于实际测验中含多种认知诊断模型的混合题库。

submitted time 2020-09-02 Hits1989Downloads467 Comment 0

5. chinaXiv:202008.00081 [pdf]

认知诊断CAT选题策略:特征,关系及新进展

唐倩; 毛秀珍; 何明霜; 何洁
Subjects: Psychology >> Psychological Measurement

随着认知诊断计算机化自适应测验(cognitive diagnostic computerized adaptive testing, CD-CAT)理论与实践的发展,兼顾知识状态与能力的双目标CD-CAT逐渐受到重视。选题策略是CAT的核心,通过梳理传统CD-CAT和双目标CD-CAT选题策略的研究,并对它们的特点、关系及表现进行介绍和评析。最后,基于认知诊断模型与CAT实践发展指出未来应加强一般化认知模型、复杂测验条件认知诊断模型下选题策略的研究;应开发双目标诊断测验的项目和测验特征指标;还应加强非参数选题方法和CD-CAT的实践应用研究。

submitted time 2020-08-19 Hits2350Downloads504 Comment 0

6. chinaXiv:202008.00080 [pdf]

基于CAT的在线标定:设计与方法

张雪琴; 毛秀珍; 李佳
Subjects: Psychology >> Psychological Measurement

项目增补是题库建设和维护的重要手段,而标定新题参数是项目增补的重要内容。 在线标定设计和在线标定方法分别研究新题的施测方式和参数估计方法,是计算机化自适应测验(computerized adaptive testing, CAT)情景下项目增补的核心技术。重点厘清在线标定设计与在线标定方法的发展思路和脉络,并对它们的特点、联系和表现进行介绍和评价。未来应基于其他信息指标进一步研究在线标定设计,可基于联合估计和误差校正的思路探究在线标定方法,应加强研究认知诊断CAT和多维CAT的在线标定技术,深入开展项目增补方法的实证研究。

submitted time 2020-08-19 Hits1010Downloads508 Comment 0

7. chinaXiv:202002.00087 [pdf]

多维对数正态作答时间模型:对潜在加工速度多维性的探究

詹沛达; Hong Jiao; Kaiwen Man
Subjects: Psychology >> Psychological Measurement

在心理与教育测量中,潜在加工速度反映学生运用潜在能力解决问题的效率。为在多维测验中探究潜在加工速度的多维性并实现参数估计,本研究提出多维对数正态作答时间模型。实证数据分析及模拟研究结果表明:(1)潜在加工速度具有与潜在能力相匹配的多维结构;(2)新模型可精确估计个体水平的多维潜在加工速度及与作答时间有关的题目参数;(3)冗余指定潜在加工速度具有多维性带来的负面影响低于忽略其多维性所带来的。

submitted time 2020-05-25 Hits19018Downloads1662 Comment 0

8. chinaXiv:202005.00039 [pdf]

心理与教育测验中异常反应侦查新技术:变点分析法 (CPA)

张龙飞; 王晓雯; 蔡艳; 涂冬波
Subjects: Psychology >> Psychological Measurement

变点分析法(change point analysis, CPA)近些年才引入心理与教育测量学,相较于传统方法,CPA不仅可以侦查异常作答被试,还能自动精确地定位变点位置,高效清洗作答数据。其原理在于:判断作答序列中是否存在可将该序列划分为具有不同统计学属性两部分的点(即变点),并且需使用被试拟合统计量(person-fit statistic, PFS)来量化两个子序列之间的差异。未来可将单变点分析拓展至多变点,结合反应时等信息,构建非参数化指标以及将现有指标拓展至多级计分或多维测验,以提高CPA的适用广度及效力。

submitted time 2020-05-12 Hits4902Downloads1821 Comment 0

9. chinaXiv:201911.00003 [pdf]

A Markov Estimation Strategy for Longitudinal Learning Diagnosis: Providing Timely Diagnostic Feedback

Zhan, Peida
Subjects: Psychology >> Psychological Measurement

及时性诊断反馈有助于学生和教师根据当前诊断结果及时调整后续学习和教学规划。针对当前纵向学习诊断模型采用的同时性估计策略无法提供及时性诊断反馈的问题,本研究提出一种新的马尔可夫估计策略,并通过模拟研究对比探究了同时性、马尔可夫、简单分离和锚题分离四种参数估计策略的表现。结果显示四者的表现具有较高一致性且呈现如下相对优劣顺序:同时性>马尔可夫>锚题分离≥简单分离。表明新策略在略微牺牲参数估计精度的前提下,可为实践者提供及时性诊断反馈,更符合“为学习而测评”的理念和形成性评价的需求。

submitted time 2020-04-19 Hits18998Downloads1306 Comment 0

10. chinaXiv:202004.00009 [pdf]

CAN Algorithm: An Individual Level Approach to identify Consequences and Norms Sensitivities and Overall Action/inaction Preferences in Moral Decision-making

Chuanjun Liu; Jiangqun Liao
Subjects: Psychology >> Psychological Measurement

Gawronski et al. (2017) developed a CNI model to measure an agent’s norms sensitivity, consequences sensitivity, and generalized inaction/action preferences when making moral decisions. However, the CNI model presupposed that an agent considers consequences—norms—generalized inaction/action preferences sequentially, which is untenable based on recent evidence. Moreover, the CNI model generates parameters at the group level based on binary categoric data. Hence, the C/N/I parameters cannot be used for correlation analyses or other conventional research designs. To solve these limitations, we developed the CAN algorithm to compute norms and consequences sensitivities and overall action/inaction preferences algebraically in a parallel manner. We re-analyzed the raw data of Gawronski et al.(2017) to test the methodological predictions. Our results demonstrate that: (1) the C parameter is approximately equal between the CNI model and CAN algorithm; (2) the N parameter under the CNI model approximately equals N/(1 – C) under the CAN algorithm; (3) the I parameter and A parameter are reversed around 0.5 – the larger the I parameter, the more the generalized inaction versus action preference and the larger the A parameter, the more overall action versus inaction preference; (4) tests of differences in parameters between groups with the CNI model and CAN algorithm led to almost the same statistical conclusion; (5) Parameters from the CAN algorithm can be used for correlational analyses and multiple comparisons, and this is an advantage over the parameters from the CNI model. The theoretical and methodological implications of our study were also discussed.

submitted time 2020-04-03 Hits9638Downloads1032 Comment 0

123  Last  Go  [3 Pages/ 22 Totals]