摘要
Current admissions decisions in USA are based however on a selection index that is constructed from a GPA regression that estimates expected GPA. We consider a new approach in which the selection index is based directly on the quantiles of the GPA distribution. The new approach realistically assumes that student characteristics have differential impacts at different parts of the GPA distribution. The quantile method also provides admissions officers the fiexibility to target different GPA properties for the freshman class.
Current admissions decisions in USA are based however on a selection index that is constructed from a GPA regression that estimates expected GPA. We consider a new approach in which the selection index is based directly on the quantiles of the GPA distribution. The new approach realistically assumes that student characteristics have differential impacts at different parts of the GPA distribution. The quantile method also provides admissions officers the fiexibility to target different GPA properties for the freshman class.
出处
《统计研究》
CSSCI
北大核心
2004年第2期53-57,共5页
Statistical Research
