面板数据均值共同变点分析在高校在校成绩上的应用

Application of common mean breaks analysis of panel data in college performance

研究高等学校学生在校成绩对于高校教学改革具有一定指导意义。以往关于在校成绩的研究主要关注其影响因素,涉及到成绩数据的变结构分析不多。因此,文章基于面板数据均值共同变点理论,采用累积和(cumulative sum,CUSUM)比率检验统计量,并通过Monte Carlo模拟对合肥工业大学数学学院学生成绩进行变结构分析。研究结果表明:数学学院学生的8个学期在校成绩没有显著变化;在进行分专业分析时显示,信息与计算科学专业在第5学期存在显著变化,而数学与应用数学专业不存在显著变化,同时分析存在显著变化的原因,为相关部门提供政策依据。

The analysis of the students’performance in school provides guidance for the development of college education.Previous research on school performance focuses on its influencing factors,and rarely involves variable structural analysis of performance data.Therefore,based on the theory of common mean breaks of panel data,the cumulative sum(CUSUM)ratio test statistic is used and the variable structural analysis of the scores of the students from the School of Mathematics of Hefei University of Technology is analyzed by Monte Carlo simulation.The results show that there is no significant break in the scores of the students of the School of Mathematics in the eight semesters.In the analysis of the sub-specialties,there is a significant break in the information and computing science specialty in the fifth semester,while there is no significant break in the mathematics and applied mathematics specialty.The reasons for significant breaks are analyzed,and the policy basis for relevant departments is provided.