新世纪20年国内测验信度研究

Research on test reliability in China’s mainland from 2001 to 2020

随着验证性因子分析模型的应用,信度研究进入了崭新的发展阶段。新世纪前20年国内有关测验信度的研究有三条发展主线。一是基于验证性因子模型的信度发展,包括同质性系数、合成信度、最大信度等;二是数据类型的拓展,包括两水平和追踪数据的信度;三是信度用途的拓展,如评分者信度、编码者信度等。对于通常的测验(题目之间的测量误差不相关),如果α系数够高,信度就够高;否则使用合成信度。如果一个统计模型中所有变量的合成信度都很高(超过0.95),使用显变量建模与使用潜变量建模的结果差别不大;否则,使用潜变量建模较好。

With the application of confirmatory factor analysis,research on reliability has entered a new stage.In the first two decades of the 21st century,the studies on test reliability in China’s mainland show three main lines of development.The first is the development of test reliability based on confirmatory factor models,including homogeneity coefficient,composite reliability,maximum reliability,etc.The second is the expansion of data types collected by scales,including the reliability of two-level data and longitudinal study.The third is the extended use of reliability,involving rater reliability,encoder reliability,etc.For a common test(with item-errors uncorrelated each other),if the coefficientαis high enough,test reliability is acceptable;otherwise composite reliability is recommended.If the composite reliability of every variable in a statistical model is very high(over 0.95),modeling with composite scores does not differ much from modeling with latent variables.Otherwise,it is better to use latent variable modeling.