中国临床心理学杂志

现代测量理论观点下的测验偏差评价

作者：刘铁川¹ 戴海琦¹ 赵玉²

单位：1. 江西师范大学心理学院江西南昌 330022
2. 赣南医学院心理学系江西赣州 341000

分类号：R395.1

出版年,卷(期):页码：2012,20(3):346-349

摘要：

测验在当前社会广泛应用的同时,其公平性受到了社会各界的广泛关注。具备公平性的测验应是无偏差的。随着测量理论的快速发展,目前已经出现多类测验偏差评价技术用以维护测验公平,而国内测验研究与实践中所使用的方法却相对滞后。本研究从现代测量学的角度,介绍了评价测量偏差、预测偏差、等值偏差方法的最新进展,并给出了使用建议。这些方法关注测验偏差的不同角度,但紧密相联。我国各行业的测验工作者应充分利用这些理论技术来指导测验的编制、使用,以促进测验的公平性。

While tests are widely used in our society, its fairness has been concerned by every social class. Fair test should be unbiased. Currently, with the rapid development of the measurement theory, there have been a variety of methods for assessing bias for maintaining test fairness. Domestic research and practice of testing lag behind the current research of test bias. The present paper has reviewed new advances of methods for assessing measurement bias, predicting bias and equating bias through the perspective of modern measurement theory. Suggestions of using these methods in practice are also given. These methods are concerned about test bias in different perspectives, though closely related. Researchers in any area of using tests and examinations should take advantage of these theories and techniques to guide the development and use of tests for promoting the test fairness.

基金项目：

高等学校博士学科点专项科研基金联合资助课题(20103604110002);国家自然科学基金(31100756);江西省高校人文社会科学研究青年基金(XL1003)资助

作者简介：

参考文献：

[1] American Educational Research Association,American Psychological Association,National Council on Measurement in Education. Standards for educational and psychological testing[M].Washington,DC,American Educational Research Association,1999.
[2] Society for Industrial and Organizational Psychology. Principles for the validation and use of personnel selection procedures[M].Bowling Green,OH,Society for Industrial and Organizational Psychology,2003.
[3] Xiaoming Xi. How do we go about investigating test faimess[J].Language Testing,2010,(02):147-170.
[4] Camilli G,Shepard LA. Methods for identifying biased test items[M].CA:Sage.Thousand Oaks,1994.
[5] Hidalgo MD,López-Pina JP. Differential item functioning detection and effect size:A comparison between logistic regression and Mantel-Haenszel procedures[J].Educational and Psychological Measurement,2004,(06):903-915.doi:10.1177/0013164403261769.
[6] Penfield RD,Camilli G. Differential item functioning and item bias[A].Amsterdam:Elsevier Science,2007.125-168.
[7] Seock-Ho K,Cohen AS. A comparison of Lord's ChiSquare,Raju's area measures,and the likelihood ratio test on detection of differential item functioning[J].Applied and Measurement in Education,1995,(04):291-312.
[8] Camilli G. Test fairness[A].CT:ACE/Praeger.Westport,2006.
[9] Pastor DA. The use of multilevel item response theory modeling in applied research:An illustration[J].Applied and Measurement in Education,2003,(03):223-243.
[10] Magis D,Beland S,Tuerlinckx F,De Boeck P. A general framework and an R package for the detection of dichotomous differential item functioning[J].Behavior Research Methods,2010,(03):847-862.
[11] Cleary TA. Test bias:Prediction of grades of Negro and White students in integrated colleges[J].Journal of Educational Measurement,1968,(02):115-124.
[12] Kyei-Blankson,Lydia S. Predictive validity,differential validity,and differential prediction of the subtests of the medical college admission test[D].Ohio University,United States,2005.
[13] Meade AW,Tonidandel S. Not seeing clearly with cleary:What test bias analyses do and do not tell us[J].Industrial and Organizational Psychology,2010,(02):192-205.
[14] Meade AW,Fetzer M. Test bias,differential prediction,and a revised approach for determining the suitability of a predictor in a selection context[J].Organizational Research Methods,2009,(04):738-761.
[15] Kim W,Nering M. Evaluation of equating items using DFIT[A].Chicago,IL,2007.
[16] Bock R,Muraki E,Pfeiffenberger W. Item pool maintenance in the presence of item parameter drift[J].Journal of Educational Measurement,1988,(04):275-285.
[17] Huiqin H,Rogern WT,Vukmirovic Z. Investigation of IRT-based equating methods in the presence of outlier common items[J].Applied Psychological Measurement,2008,(04):311-333.doi:10.1177/0146621606292215.
[18] Kolen MJ. Population invariance in equating and linking:Concept and history[J].Journal of Educational Measurement,2004,(01):3-14.
[19] Dorans N J,Holland PW. Population invariance and the equatability of tests:Basic theory and the linear case[J].Journal of Educational Measurement,2000,(04):281-306.
[20] yon Davier AA,Wilson C. Investigating the population sensitivity assumption of item response theory true-score equating across two subgroups of examinees and two test formats[J].Applied Psychological Measurement,2008,(01):11-26.doi:10.1177/0146621607311560.
[21] Yi Q,Harris DJ,Gao X. Invariance of equating functions across different subgroups of examinees taking a science achievement test[J].Applied Psychological Measurement,2008,(01):62-80.doi:10.1177/0146621607311579.
[22] Liu M,Holland PW. Exploring population sensitivity of linking functions across three law school admission test administrations[J].Applied Psychological Measurement,2008,(01):27-44.doi:10.1177/0146621607311576.
[23] yon Davier AA,Holland PW,Thayer DT. The chain and post-stratification methods for observed-score equating and their relationship to population invariance[J].Journal of Educational Measurement,2004,(01):15-32.

服务与反馈：

【文章下载】【加入收藏】