A Logistic Regression Model For The Enhancement Of Student Retention: The Identification Of At-Risk Freshmen

Main Article Content

Joseph G. Glynn
Paul L. Sauer
Thomas E. Miller

Keywords

Abstract

A logistic regression model will be developed to provide early identification of freshmen at risk of attrition. The early identification is accomplished literally within a couple of weeks after freshman orientation. The dependent variable of interest is persistence, and it is a binary, nominal variable. Students who proceed from freshman matriculation to graduation without ever having dropped out are labeled persistors. Freshman matriculates who leave college either temporarily or permanently are classified as dropouts. The independent variables employed to predict attrition include demographics, high school experiences, and attitudes, opinions, and values as reported on a survey administered during freshman orientation. The model and its results will be presented along with a brief description of the institutional intervention program designed to enhance student persistence.

Downloads

Download data is not yet available.
Abstract 515 | PDF Downloads 737