锚测验难度参数方差特征对测验等值的影响研究  

The Effect of Anchor Tests with a Spread of Item Difficulties on Test Equating

作　　者：曹文娟[1] 白俊梅[1] 

机构地区：[1]江西师范大学心理学院

出　　处：《考试研究》2013年第3期79-85,33,共8页Examinations Research

摘　　要：本文使用R-2.15.2软件模拟研究锚测验难度参数方差特征对测验等值误差的影响,采用三种等值方法(链百分位等值法、Levine等值法和Tucker等值法)对锚测验不同类型的难度方差进行比较研究。结果显示,当锚测验难度方差小于全测验难度方差时,其等值的随机误差和系统误差与锚测验难度方差和全测验难度方差一致时(即锚测验为全测验的平行缩减版minitest时)的表现基本相同。因此,对锚测验而言,要求其与全测验具有相同的统计规格可能过于严格。This paper used R-2.15.2 Software to achieve simulation data to study the effect of anchor tests with a spread of item difficulties on test equating. Using three equating methods （ Chain Equipercentile Equating, Levine Method and Tucker Method） to compare several types of anchor tests. The results demonstrate that anchor test with a spread of item difficulties less than that of a total test seems to perform as well as a minitest with respect to equating bias and equating standard error. Hence, requiring an anchor test to have the same statistical characteristics as the total test may be too restrict.

关 键 词：锚测验 非等组设计 等值方法 百分位等值法 

分 类 号：G424.74[文化科学—课程与教学论]