分位回归模型在数学成绩分析中的应用  

Application of Quantile Regression Model in Mathematics Scores Analysis

作　　者：刘紫璇 刘新红[1] 郭蕾 胡继飞 徐英杰 LIU Zixuan;LIU Xinhong;GUO Lei;HU Jifei;XU Yingjie(Beijing Institute of Petrochemical Technology,Beijing 102617,China)

机构地区：[1]北京石油化工学院

出　　处：《北京石油化工学院学报》2019年第3期65-70,共6页Journal of Beijing Institute of Petrochemical Technology

基　　金：大学生研究训练计划项目(2018J00149);北京石油化工学院教学改革和研究项目(YB20170801);北京市教委科研计划、社科计划一般项目(KM201710017004)

摘　　要：高校数学类课程的考试成绩是每个高校学生数学素质的综合体现,但现实中存在诸多影响数学类课程成绩的因素。从我校某专业学生的数学类课程成绩出发,采用分位回归模型建立了概率统计与高考数学、高等数学及线性代数之间的关系。通过实证分析揭示了造成概率统计成绩水平不一的影响因素,并与普通最小二乘回归结果进行对比,从而得到更全面的信息,为提升我校数学素质提供实证依据。The examination scores of mathematics courses in Colleges and universities are the comprehensive reflection of each college student s mathematics quality.But actually there are many factors that affect students performance in mathematics courses.In this paper,the connection between probability and statistics,and mathematics in college entrance examination,higher mathematics and linear algebra is researched and clarified by using the quantile regression model based on the scores of mathematics courses of students from some particular major.Through the empirical analysis,this paper reveals the factors that cause different levels of probability and statistics,and compares them with the results of ordinary least squares regression,so as to get more comprehensive information and provide the empirical evidence for improving students mathematical quality.

关 键 词：分位回归 正态分布检验 参数估计 

分 类 号：F840[经济管理—保险]