多元概化理论在高等教育自学考试命题质量控制中的应用——以北京市《英语水平考试(一)笔试》为例  

Application of Multivariate Generalizability Theory in Quality Control in Test Development of the Self-taught Examination

作　　者：田霖[1] 王桥影[1] 赵晓茫[1] 

机构地区：[1]北京教育考试院

出　　处：《考试研究》2012年第3期57-64,共8页Examinations Research

基　　金：北京市2011年财政项目"高等教育自学考试标准化题库建设"(PXM2011_014256_111831)资助

摘　　要：概化理论作为新一代测量理论逐渐应用于大规模考试领域。文章运用多元概化理论对自学考试课程《英语水平考试(一)笔试》试卷的测量信度、试卷总分合成、及格线决策信度、试卷结构优化等问题进行探讨。研究发现:本次考试的测量信度较高;各分测验对全域总分的方差贡献比例与试卷赋分意图基本一致;该试卷以60分作为及格线具有较高的决策信度;将各分测验题量同时增至15题或单独将词汇分测验题量增至20题,可有效提高测量信度。Generalizability Theory （GT）, as one of new test theories, is gradually applied to large-scale tests. In this article, we adopted Multivariate Generalizability Theory （MGT） to appraise test reliability, combination of scores, decision based on data of English Proficiency Test One reliability of cut-off score, test structure optimization The result shows that： a） the reliability coefficient of whole test is acceptably high, b） the ratio of each subtest＇ s contribution to total variance is in accordance with test-setters＇ anticipation, c） high decision reliability is gained by setting 60 per cent as the cut-off score, d） to promote test reliability, it is recommended to increase the sample size of each subtest to 15 or increase the sample size of subtest one to 20 alone.

关 键 词：多元概化理论 自学考试 可靠性指数 决策信度 

分 类 号：G424.74[文化科学—课程与教学论]