Rule-based Item Generation of Algebra Word Problems Based upon Linear Logistic Test Models für Item Cloning and Optimal Design

基于用于项目克隆和优化设计的线性 Logistic 测试模型的代数应用题的基于规则的项目生成

• 批准号: 43742131
• 负责人: Professor Dr. Heinz Holling
• 金额: --
• 依托单位: Department of Research Methodology, Measurement and Data Analysis
• 依托单位国家: 德国
• 项目类别: Priority Programmes
• 财政年份: 2007
• 资助国家: 德国
• 起止时间: 2006-12-31 至 2009-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/43742131?language=en
• 关键词: Rule; based; Item; Generation; Algebra

Techniques from item response theory (IRT), hierarchical modelling, knowledge structures, cognitive diagnosis models, and optimal design theory are combined to develop procedures for automated item generation and test assembly for the testing of basic statistical competencies in upper secondary and higher education, as can be assessed with statistical word problems. It will also be investigated how the models and procedures should be optimized and generalized when they are applied in computerized adaptive testing, testing for diagnosis, and large-scale educational assessments. The final goal is the development of a software program which adaptively generates tailor-made items for statistical word problems based on optimal design, linear-logistic test models, and models for test item cloning. During the first phase of the project, cognitive rules for generating statistical world problems have been identified and field tested and models for rule-based item generation have been developed and made statistically tractable. The current grant application is for the next two years in which the research will focus on the improvement of the cognitive rules, development of statistical tests for the goodness of fit of the models, empirical studies to validate cognitive rules and test the models, and the application of optimal design principles to automate test assembly. In addition and beyond the first application period, knowledge structures and cognitive diagnosis models will be adapted to our models and empirical data.

项目反应理论（IRT）、分层建模、知识结构、认知诊断模型和优化设计理论的技术相结合，开发了用于高中和高等教育基本统计能力测试的自动化项目生成和测试组装程序，可以用统计单词问题进行评估。本文还将研究这些模型和程序在计算机化自适应测试、诊断测试和大规模教育评估中应用时应如何优化和推广。最终目标是开发一个软件程序，该软件程序可以根据最佳设计、线性逻辑测试模型和测试项目克隆模型，自适应地为统计单词问题生成量身定制的项目。在项目的第一阶段，已经确定并实地测试了产生统计世界问题的认知规则，开发了基于规则的项目生成模型，并使其在统计上易于处理。目前的拨款申请是在未来两年，研究将集中在改进认知规则，开发模型拟合优度的统计测试，验证认知规则和测试模型的实证研究，以及应用最优设计原则自动化测试组装。此外，在第一个应用阶段之后，知识结构和认知诊断模型将适应我们的模型和经验数据。