A plethora of research spanning several decades has attempted to understand predictors of retention and graduation in undergraduate bachelor's degree programs. The topic is no less important today, as larger and larger swaths of the American population attend college each year. Studies have demonstrated that key demographic variables, indicators…

A logit model predicting student outcomes for a gateway course, Math for Liberal Arts, was successfully developed which fits the data well. Two variables, ACT math score and high school GPA, were found to be significant predictors of achieving a C or better in Math for Liberal Arts. A practical implication of the study suggests that with just two…

Three versions of a probabilistic model adapted from the theory of information retrieval--a binary version, a version using the full value of the data, and a version using principal components--were tested and applied to data available from application forms to predict graduate school performance of library school students. (EM)