2010至2012年全国硕士研究生入学西医综合考试多元概化理论研究

Study of 2010-2012 western medicine comprehensive test in postgraduate entrance examina-tion based on multivariate generalizability theory

目的：该研究全面评估2010至2012年西医综合考试的总体信度、试卷结构、二级学科比例分配的合理性等指标，为今后修订大纲和改进测验质量提供参考依据。方法抽取2010至2012年15765名考生考后数据，应用多元概化理论，分别从学科因子和题型因子角度进行概化研究和决策研究的统计分析。结果①关于学科因子分析，基础学科的方差分量相对较高，全域总分的相对误差很小，概化系数均在0.930以上。②关于题型因子分析，总体上X型题和A1型题的方差分量相对较高，全域总分的相对误差很小，概化系数均在0.930以上。结论①从考查的学科内容看，各学科测量精度均较高，基础学科的贡献相对高于临床学科，进一步提高试题区分度有利于进一步提高测量精度。②从题型设计看，各题型测量误差小，测量精度高，各题型的分量分布较合适，A3型题的试题分量可进一步提高。

Objective To systematically evaluate the overall reliability,test paper structure and rationality proportional distribution of the secondary discipline of western medicine comprehensive test papers from 2010 to 2012 to provide references for future improvement to the syllabus and test quality. Methods Data of 15 765 candidates from 2010 to 2012 were extracted and statistical analy-sis was performed to do generalized research and decision-making research from discipline factors and question type factors. Results ①Based on the discipline factor analysis,variance components of ba-sic disciplines were relatively high ,global score relative error was very small and the generalizability coefficient was above 0.930. ②Based on the question type factor analysis,variance components in X-type questions and A1-type questions were relatively high, global score relative error was very small and the generalizability coefficient was above 0.930. Conclusions ①From the discipline content, the accuracy of various disciplines is high;contribution of basic disciplines is relatively higher than that of clinical disciplines;further improving the discrimination of questions can help to improve measure-ment accuracy. ②From the question design,question measurement error is small,accuracy is high,and the question distribution is appropriate;scale of A3 type questions can be further improved.