基于IRT的三年级数学成就测验的编制  

Construction of Mathematics Achievement Test for Grade 3rd in IRT

作　　者：范晓玲[1] 魏勇[1] 

机构地区：[1]湖南师范大学教科院心理系,湖南长沙410081

出　　处：《中国临床心理学杂志》2006年第1期11-12,16,共3页Chinese Journal of Clinical Psychology

基　　金：湖南省教育厅科学研究项目

摘　　要：目的:尝试在项目反应理论的指导下,编制三年级数学成就测验,为学科学习的评价提供一辅助工具。方法:用贝佳方法检验试测数据单维性,利用ANOTE软件估计项目参数,采用铆测验设计进行参数等值。结果:四套试卷均符合单维性要求,基本拟合三参数逻辑斯蒂克模型,项目拟合度都在90%左右,最终选取52个项目组成正式测验。结论:正式测验的信息量达到31.1548,估计标准误为0.1267,符合项目反应理论的要求。Objective： Under the guidance of the item response theory, the author designed the mathematics achievement test and provided a subsidiary test for the evaluation of the performance of mathematics of grade 3, Methods： A two-way specification table was designed before the experiment, The Bejar method was carried out on the data collected, the parameter was evaluated by ANOTE software, the research adopted Anchor-test design,and finished the item parameter equating. Results： All the resuhs were in accordance with the request of unidimensionality, the data fitted Three-Parameter Logistic Model, and finally 52 items were selected to constitute the formal test. Conclusion： The formal test information reaches 31.1548,SE=0.1267, which is accorded with the requirements of the item response theory.

关 键 词：数学成就测验 3PL模型 项目参数等值 测验信息量 

分 类 号：G449.5[哲学宗教—心理学]