Configural Invariance of a Model of Student Attrition

The model presented used available data to predict whether or not a student will drop out at some time during his or her college career. The model successfully identified students who would or would not drop out approximately 80% of the time. Logistic regression analysis was employed to predict chances of attrition for matriculating freshmen soon after freshman orientation. The dependent variable was the probability a student would, at some time in their college experience, drop out of college. The independent or predictor variables included demographics, high school experiences and factor scores based on a survey of attitudes, opinions and values. A two-stage procedure consisting of factor analysis in the first stage and logistic regression in the second stage provided model parameter estimates for each cohort of matriculating freshman in years 2000 to 2003. Empirical tests revealed the model was fully configural invariant in the first stage and partially configural invariant in the second stage.