An Economic Analysis of Student Loan Default

Abstract

An existing model of student loan default uses discriminant function analysis to identify the characteristics of borrowers who repay their loans and those who default. This paper uses data on National Direct Student Loan borrowers at the University of North Carolina at Greensboro to confirm the results of a previous paper’s discriminant function analysis and to present an alternative method of analysis, the Tobit technique. An advantage of Tobit is that it uses information not only from the categorical default/no default decision but also from the magnitude of the default.