Paul Attewell, Matt Giani, Tod R. Massa, and Nathan Wilson (Presented at 2019 AERA Annual Meeting)
This paper reports the results of a four-state collaboration that uses Student Unit Record Systems that track students from high school into college. The goal is to determine whether it is possible to accurately predict or identify which students will not graduate using very early indicators – variables available at college entry or during the first semester. Using statistical models we are able to identify those students at greatest risk of non-completion quite accurately at this very early stage, allowing college staff to prioritize interventions and supports aimed at improving retention and completion for those at greatest risk. Our models do not use gender, race or ethnicity in determining probability of non-completion.