-
摘要: 大规模教育考试的维度与考试分数的意义解释、考生在考试中的行为表现解释密切相关。利用非参数项目反应理论模型选择试题组成单维量表, 可以达到研究考试维度的目的。选择单维量表试题时, 下界c值的确定, 是个值得探讨的问题。用非参数项目反应理论模型对英语考试的三个量表维度研究发现, 从每一个量表中只能选择出一个单维量表, 而不是与每一部分测量的微技能数相应的多个单维量表; 每一单维量表测量的均为该部分不同微技能的组合。这个特征表明这些单维量表均为基本单维量表, 非严格单维量表。无论c值为0.3, 还是0.2, 选择出的基本单维量表均满足弱单调性要求, 整个单维量表的区分功能不会有明显差异。
-
关键词:
- 非参数项目反应理论模型 /
- 教育考试 /
- 维度 /
- 单维量表
-
图 4 单维量表试题回归平均曲线
图 4说明:细实线为听力单维量表回归平均值曲线; 粗短划线为阅读部分单维量表回归平均值曲线; 点线为阅读听力混合单维量表回归平均值曲线。每一部分曲线中, 左上相应于c=0.3时的单维量表; 右下相应于c=0.2时的单维量表。
-
[1] Abswoude, A.A.H. & Andries, L.Ark, van der et al.(2004).A comparative study of test data dimensionality assessment procedures under nonparametric IRT Models.Applied Psychological Measurement, 28 (1). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1177/0146621603259277 [2] Abswoude, A.A.H. & Vermunt, J.K.et al.(2004).Mokken scale analysis using hierarchical clustering procedures.Applied Psychological Measurement.28 (5). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=10.1177/0146621604265510 [3] Bacon, D.R.(2001).An evaluation of cluster analytic approaches to initial model specification.Structural Equation Modelling. [4] Mokken, R.J. & Lewis, C.(1982).A non parametric approach to the analysis of dichotomous item responses.Applied Psychological Measurement.6:417-430 doi: 10.1177/014662168200600404 [5] Mokken, R.J.(1997).Nonparametric models for dichotomous response.In: Linden, W.J.van der.Hambleton, R.K. Handbook of Modern Item Response Theory.New York: Springer, 351-367 [6] Molenaar, I.W. & Sijtsma, K.(2000).Users manual MSP5 for windows: A program for Mokken scale analysis for polytomous items [Software manual].Groningen, the Netherlands: iec ProGARAMMA, [7] Molenaar, I.W.(1983).Some improved diagnostics for failure of Rasch model.Psychometrika, 48:49-72 http://www.onacademic.com/detail/journal_1000034942026010_3505.html [8] Sijtsma, K. & Molenaar, I.W.(2002).Introduction to nonparametric item response theory.London: International Educational and Professional Publisher [9] Stout, W.F.(1990).A new response theory modeling approach with applications to unidimensionality assessment and ability estimation.Psychometrika, 55:293-325 doi: 10.1007/BF02295289 [10] Stout, W.F. & Habing, B.et al.(1996).Conditional covariance-based nonparametric multidimensionality assessment.Applied Psychological M easurement.20:331-354 doi: 10.1177/014662169602000403 [11] Zhang, J. & Stout, W.F.(1999).Conditional covariance structure of generalized compensatory multidimensional items.Psychometrika, 64:129-152 doi: 10.1007/BF02294532