Daniel R. Jones-White, Peter M. Radcliffe, Ronald L. Huesman Jr., John P. Kellogg, Redefining Student Success: Applying Different Multinomial Regression Techniques for the Study of Student Graduation Across Institutions of Higher Education, Research in Higher Education, March 2010, Volume 51, Issue 2, pp.154-157.
The article tackles a perceived flaw in standard evaluations of student success. Moving away from binary all-or-nothing classifications of ‘graduate’ or ‘drop-out’, Jones-White et al device a more sophisticated method. Through the analysis of data from the National Student Clearinghouse (NSC), the method takes into account retention and graduation numbers at both entry and transfer institutions. Hence, what they accomplish is to construct a polychotomous definition of success. The challenge facing them include identifying new methods to model limited dependent variables. They are sceptical that the multinomial logit method is apt for the . . . Read More