Application of Statistical Classification Analysis to Engineering Student Recruitment

这个探索性项目将运用统计分类分析对大学录取数据进行分析，以确定那些影响学生的变量。他选择工程学作为第一，也许也是唯一的主修领域。变量，如入学考试成绩，高中GPA，社会经济地位，种族，性别，完成的工程预科课程，以及其他被怀疑影响青少年的因素？S决定学习工程，将被审查，以确定他们在这个决定中的作用。具体来说，统计逻辑回归、分类树和最近开发的随机森林技术将应用于德克萨斯理工大学录取的学生样本。一旦完成，这些技术将对变量进行分类，并产生一个预测模型，用于招收学习工程的学生。然后，这些发现可以被工程界用来设计课程、课程和招聘计划，既能吸引学生，又能以更符合他们期望和能力的方式向学生介绍工程学习。改善招聘和保留策略将有助于增加国家所需的工程专业毕业生的数量。这个项目的结果将成为指导工程专业招收学生的资源。该项目将应用最近开发的统计分类技术对一个大数据样本，可以同时过滤许多变量，并确定每个变量的重要性。通过对学生在进入大学之前选择工程专业的原因的进一步了解，可以改善工程专业学生的一般招聘。利用这些结果，旨在增加工程专业学生人数的努力和举措可以集中在重要的决策变量上。这些发现对于设计和实施工程专业学生招聘计划的大学招聘人员也很重要。

This exploratory project will apply statistical classification analysis to college admission data to identify those variables that impact a student?s choice of engineering as the first and perhaps only major field of study. Variables, such as entrance exam scores, high school GPA, socio-economic status, ethnicity, gender, pre-engineering courses completed, and other factors that are suspected to influence an adolescent?s decision to study engineering, will be examined to determine their role in this decision. Specifically, statistical logistic regression, classification tree, and recently developed random forest techniques will be applied to a sample of students admitted to Texas Tech University. Once accomplished, these techniques will classify the variables and yield a predictive model for student recruitment to study engineering. These findings can then be used by the engineering community to design courses, curricula and recruitment programs that both attract students and also introduce students to the study of engineering in a manner more consistent with their expectations and abilities. Improved recruitment and retention strategies will help increase the number of engineering graduates needed by the nation?s workforce, and the results of this project will be a resource for guidance about recruiting students to engineering programs. This project will apply recently developed statistical classification techniques to a large data sample and can filter through many variables simultaneously and identify the significance of each variable. General recruitment of engineering students can be improved by taking advantage of this additional insight into why students select engineering prior to entering college. Using these results efforts and initiatives directed towards increasing the number of students enrolling in engineering can be focused on to the significant decision variables. The findings will also be important for college recruiters as they design and implement engineering student recruitment programs.