ARRG法在消除随机猜答影响中的应用研究综述  

Review of ARRG Method to Remove the Influence of Random Guessing Responses

作　　者：王风 孔祥[1] WANG Feng;KONG Xiang(Beijing Language and Culture University,Beijing 100083,China)

机构地区：[1]北京语言大学,北京100083

出　　处：《中国考试》2021年第3期45-49,共5页journal of China Examinations

基　　金：国家社科基金2015年度重大项目“汉语交际能力标准与测评体系研究”(15ZDB101)。

摘　　要：Rasch模型框架下,考生能力和题目难度的不匹配会导致考生猜测作答现象的出现,ARRG法的提出即是为了消除考生猜测作答对参数估计的影响。ARRG法通过原始分析、裁剪分析、锚分析和全锚分析,能够实现题目难度和能力参数的调整,该方法中概率阈限的设置、样本量的选择及结果的比较也是需要关注的重点。Under the framework of Rasch model,the mismatch between candidates’ability and question difficulty will lead to the phenomenon of candidates’guessing responses.The ability removing random guessing(ARRG)method is proposed to eliminate the influence of candidates’guessing responses on parameter estimation.ARRG method can adjust the problem difficulty and ability parameters through original analysis,tailored analysis,anchored analysis and all-anchored analysis.At the same time,the setting of probability threshold,the selection of sample size and the comparison of results in this method are also the key points that need to be paid attention to.

关 键 词：RASCH模型 猜测作答 试题难度 ARRG法 锚分析 裁剪分析 

分 类 号：G405[文化科学—教育学原理]