多维测验分数的报告与解释:基于双因子模型的视角  

Reporting and Interpreting Multidimensional Test Scores:A Bi-factor Perspective

作　　者：顾红磊[1] 温忠麟[2] 

机构地区：[1]信阳师范学院教育科学学院,信阳464000 [2]华南师范大学心理应用研究中心/心理学院,广州510631

出　　处：《心理发展与教育》2017年第4期504-512,共9页Psychological Development and Education

基　　金：国家自然科学基金项目(31400909;31271116);国家社会科学基金项目(17BTJ035);信阳师范学院"南湖学者奖励计划"青年项目~~

摘　　要：在心理、行为、管理和教育等社科领域,经常使用多维测验。本文评介并比较了各种多维测验的测量模型;总结了基于双因子模型计算得到的统计指标;根据不同研究目的,提出了两个兼顾简洁性和精确性的多维测验分析流程。作为例子,在马基雅维利主义人格量表的研究中,通过双因子模型分析了如何报告、解释多维测验分数以及如何利用多维建模进行后续分析。Empirical psychological, educational and social scientists are often confronted with multifaceted tests which are comprised of several related dimensions or subtests. This study is organized as follows ： Firstly, the meas- urement models of multidimensional scales were reviewed and evaluated. Secondly, some statistical indices （i. e. , ECV, PUC and four types of reliability coefficients） based on hi-factor modeling were calculated and interpreted. Thirdly, based on different research purposes, we summarized and proposed two analysis processes about multidi- mensional measurement, and both of them took the simplicity and accuracy into account simultaneously. Finally, as an example, the hi-factor model of the Machiavellianism Personality Scale （MPS） was analyzed, and the following questions were clarified for applied researchers： Do total scores generally reflect variation on a single latent varia- ble？ Is it justified to report the subscale scores？ After partitioning out variability attributed to the total score, could subscales still provide reliable information？ Could a complex multidimensional measurement be modeled using a simple unidimensional CFA？

关 键 词：多维测验 双因子模型 同质性系数 共同变异解释比 

分 类 号：B844[哲学宗教—发展与教育心理学]