A nonparametric approach to assess undergraduate performance

TL;DR

This paper introduces a nonparametric method using generalized U-statistics to evaluate undergraduate performance, accounting for gender and high school sector, providing a more accurate assessment than traditional measures like GPA.

Contribution

The paper develops a novel nonparametric approach for assessing student performance through pairwise comparisons and statistical tests, addressing limitations of GPA-based evaluations.

Findings

The method effectively compares student performance across groups.

Asymptotic normality of the test statistic is established.

Maximum test power is achieved using the union intersection principle.

Abstract

Nonparametric methodologies are proposed to assess college students' performance. Emphasis is given to gender and sector of High School. The application concerns the University of Campinas, a research university in Southeast Brazil. In Brazil college is based on a somewhat rigid set of subjects for each major. Thence a student's relative performance can not be accurately measured by the Grade Point Average or by any other single measure. We then define individual vectors of course grades. These vectors are used in pairwise comparisons of common subject grades for individuals that entered college in the same year. The relative college performances of any two students is compared to their relative performances on the Entrance Exam Score. A test based on generalized U-statistics is developed for homogeneity of some predefined groups. Asymptotic normality of the test statistic is true for both null and alternative hypotheses. Maximum power is attained by employing the union intersection principle.