结构化面试评定量表的现代测量学分析被引量：10

A Rating Scale Analysis by Using the Modern Test Theory

下载PDF

导出

摘要结构化面试作为使用最为普遍的人事选拔技术之一受到越来越多研究者的关注。本研究与传统分析方法和内容不同,选用IRT的Rasch模型的拓展——多面Rasch模型,对某次结构化面试中两组12位评委对66名考生的面试数据进行分析,主要对面试中10点量表的使用进行了检测。结果表明:在面试的五个维度中,10点量表并未完全使用,低端的3个等级未被使用;总体而言,考生在各维度上得到的评定越高就越有能力,但在综合分析和口头表达两个维度上,出现了等级评定和考生能力倒挂现象;而且,在各个面试维度上均发现了评定等级的非等距性。 Being one of the most popular techniques in personnel selection practice, the structured interview has attracted more and more research interest. Different from traditional analyses, this study focused on the quality of the rating scale used by raters in a structured interview consisting of 66 interviewees and two panels. Raters in the panels rated interviewees on five dimensions with a 10-point rating scale. The results showed that： 1. among all 10 points, not all of them were used. Specifically, none of 1-3 was used by the raters. 2. Generally speaking , the higher an interview- ee scored, the more able he was, but there were two exceptions：on the general analysis dimension and the oral expressiveness dimension. 3. Different from what was generally assumed, the points on the rating scale were not evenly spaced.

作者孙晓敏张厚粲

机构地区北京师范大学心理学院应用实验心理北京市重点实验室

出处《应用心理学》 CSSCI 2007年第3期250-256,共7页 Chinese Journal of Applied Psychology

基金北京师范大学青年教师人文社会科学研究基金项目

关键词结构化面试评定量表多面RASCH模型 structured interview rating scale, Many-Facet Rasch Model

分类号 B841 [哲学宗教—基础心理学]

引文网络
相关文献

参考文献13

1Lunz M E, Wright B D, Linacre J M. Measuring the impact of judge severity on examination scores. Applied Measurement in Education, 1990,3 (4) :331.
2Hambleton R K, Jones R W. Comparison of classical test theory and item response theory and their applications to test development. Educational Measurement Issues and Practice, 1993,12:38 - 47.
3孙晓敏,张厚粲.国家公务员结构化面试中评委偏差的IRT分析[J].心理学报,2006,38(4):614-625. 被引量：36
4Lunz M E. Variation among Examiners and Protocols on Oral Examinations. San Francisco, CA : 1989.
5Myford C M, Wolfe E W. When raters disagree, then what: Examining a third- rating discrepancy resolution procedure and its utility for identifying unusual patterns of ratings. Journal of Applied Measurement. 2002,3 (3) :300 - 324.
6Myford C M, Engelhard G J. Examining the psychometric quality of the national board for professional teaching standards early childhood/generalist assessment system. Journal of Personnel Evaluation in Education. 2001,15 (4) :253.
7Marcoulides G A, LurLz M E, Linacre J M. Measurement designs using multifacet Rasch modeling. Mahwah, NJ, US : Lawrence Erlbaum Associates Publishers, 1998:47 - 77.
8Myford C M. Investigating design features of descriptive graphic rating scales. Applied Measurement in Education. 2002, 15(2) :187 -215.
9Linacre J M. Facets for Windows 3.62.0 ed. Chicago : MESA Press ,2007.
10Linacre J M. Investigating rating scale category utility. Journal of Outcome Measurement. 1999,3 (2) : 103.