摘要
主观性试题具有题量少、存在评分员误差的特点,在评分时较少进行等值。不同的主观性试题间难免会存在难度差异,若能进行等值则可大大降低难度差异、保证考试公平性。研究尝试在无锚题情境下,构造"准锚",期望实现主观题的等值连接。实验以MHK口试数据为研究对象,找出难度近似的朗读题作为"准锚题",并在等级反应模型下采用非等组锚题设计进行了等值连接。结果表明,朗读题作锚具有可行性,是一种有效的试后等值的方法。
Subjective Items usually consist of only a few questions and are always influenced by rating errors,yet they are rarely be equated in scoring.Different subjective items will inevitably have difficulty differences.If equivalence can be carried out,the difficulty differences can be greatly reduced and the fairness of the test can be guaranteed.This study attempts to construct“quasi-anchor”in the condition of no anchor items in order to achieve equivalent connection of subjective items.Taking MHK oral test data as the research object,the experiment tries to find out the reading-aloud items with similar difficulty as“quasianchor items”,and uses the non-equivalent groups with anchor test design to carry out equivalent connection within the Graded Response Model.The results show that it is feasible to use reading-aloud items as quasi-anchor items,and it is an effective post-examination equivalence method.
作者
陈梦琳
吕欣
CHEN Menglin;LV Xin(Faculty of Linguistic Sciences,Beijing Language and Culture University;Institute on Educational Policy and Evaluation of International Students,Beijing Language and Culture University)
出处
《语言规划学研究》
2020年第1期74-83,共10页
Journal of Language Planning
基金
国家社科基金重大项目“汉语交际能力标准与测评体系研究”(项目号:15ZDB101)阶段成果
关键词
主观性试题等值
准锚
方法探究
equivalence of subjective items
quasi-anchor item
method research