Colleges have increasingly turned to predictive analytics to target at-risk students for additional support. Most of the predictive analytic applications in higher education are proprietary, with private companies offering little transparency about their underlying models. We address this lack of transparency by systematically comparing two…

Physics education research (PER) has used quantitative modeling techniques to explore learning, affect, and other aspects of physics education. However, these studies have rarely examined the predictive output of the models, instead focusing on the inferences or causal relationships observed in various data sets. This research introduces a modern…

With the adoption of Learning Management Systems (LMSs) in educational institutions, a lot of data has become available describing students' online behavior. Many researchers have used these data to predict student performance. This has led to a rather diverse set of findings, possibly related to the diversity in courses and predictor variables…

Data mining is known to have a potential for predicting user performance. However, there are few studies that explore its potential for predicting student behavior in a procedural training environment. This paper presents a collective student model, which is built from past student logs. These logs are first grouped into clusters. Then, an…

The Pittsburgh Promise is a scholarship program that provides $5,000 per year toward college tuition for public high school graduates in Pittsburgh, Pennsylvania who earned a 2.5 GPA and a 90% attendance record. This study used a difference-in-difference design to assess whether the introduction of the Promise scholarship program directly…

The paper uses the Integrated Postsecondary Education Data system (IPEDS) data to simulate the 2020 American Graduation Initiative (AGI) goal introduced by President Obama in the summer of 2009. We estimate community college graduation rates and completion numbers under different scenarios that include the following sets of variables: (a) internal…

The increasing competition for graduate students among business schools has resulted in a greater emphasis on graduate business student retention. In an effort to address this issue, the current article uses survival analysis, decision trees and TreeNet® to identify factors that can be used to identify students who are at risk of dropping out of a…

Building on Shulruf, Hattie and Tumen (2008), this work examines the capacity of various National Certificate in Educational Achievement (NCEA)-derived models to predict first-year performance in Biological Sciences at a New Zealand university. We compared three models: (1) the "best-80" indicator as used by several New Zealand…

Classification accuracies of models for predicting later high school dropouts from data available in student records for grades 4 through 8 were examined for 503 dropouts and 282 persisters (nondropouts) in Florida. Separate prediction models for each grade level have practical importance; implications for dropout prediction are discussed. (SLD)

A discriminant analysis of objective and subjective measures from the records of students who graduated from the University of Medicine and Dentistry of New Jersey-New Jersey Medical School over a six-year period was used to generate a model for the prediction of medical specialty choice. (Author/MLW)

Due to factors such as high enrollment demands, limited institutional space, and high program costs, certain admissions requirements in the guidance/selection of students for health technology programs at Virginia Western Community College (VWCC) have become necessary. A Health Technology Admissions Evaluation System was created to develop and…