CAT模拟结果的分析模式与评价指标  

Analysis Models and Evaluation Indexes of Computerized Adaptive Testing Simulation Results

作　　者：简小珠[1,2] 戴步云[2] 陈平 

机构地区：[1]井冈山大学教师教育中心 [2]江西师范大学心理学院,江西省心理与认知科学重点实验室 [3]北京师范大学中国基础教育质量监测协同创新中心

出　　处：《中国考试》2016年第12期19-28,共10页journal of China Examinations

基　　金：江西省高校人文社会科学研究青年项目"计算机化自适应测验(CAT)测量技术与评价分析"(项目编号:XL1515)的研究成果之一

摘　　要：计算机化自适应测验(CAT)模拟是CAT研究的主要方法之一。CAT模拟结果的评价分析内容主要包括三个方面:被试能力估计与被试能力分类分析、题库试题使用情况分析和CAT测验作答过程分析。CAT模拟结果的分析模式主要分为整体分析和细化分析两种模式。本研究从测验模拟返真性能、测验准确性、题库安全性、题库使用率、测验分类效率与准确性、多测验目标约束控制的实现程度等角度概述CAT模拟结果的各类评价指标。CAT模拟结果的评价角度和评价指标需要根据CAT研究目标和测验情境要求加以确定。Computerized Adaptive Testing （CAT） simulation is one of the main methods of CAT research. Evaluation and analysis of CAT simulation results mainly includes three aspects： estimation and classification analysis of examinee ability, analysis of the utilization of the test items from the item bank and analysis of the CAT response process. Analysis of CAT simulation results mainly involves a holistie approach and a fine-grained approach. This study provides an overview of the various evaluation indexes involved in evaluating CAT simulation results from the perspectives of simulation recovery, measurement accuracy, item security, item utilization rates, examinee classification efficiency and accuracy, and control of multiple test objectives. The perspectives and evaluation indexes required for a CAT simulation study have yet to depend on the purpose and context of that study.

关 键 词：CAT CAT模拟 分析模式 评价指标 

分 类 号：G405[文化科学—教育学原理]