Knowledge tracing is the task of modeling each student's mastery of knowledge concepts (KCs) as (s)he engages with a sequence of learning activities. Each student's knowledge is modeled by estimating the performance of the student on the learning activities. It is an important research area for providing a personalized learning platform to…

Vocabulary knowledge is essential to educational progress. High quality vocabulary instruction requires supportive contextual examples to teach word meaning and proper usage. Identifying such contexts by hand for a large number of words can be difficult. In this work, we take a statistical learning approach to engineer a system that predicts…

Vocabulary knowledge is essential to educational progress. High quality vocabulary instruction requires supportive contextual examples to teach word meaning and proper usage. Identifying such contexts by hand for a large number of words can be difficult. In this work, we take a statistical learning approach to engineer a system that predicts…

School dropout is a growing concern across Latin America because of its negative social and economic consequences. Identifying who is likely to drop out, and therefore could be targeted for interventions, is a well-studied prediction problem in countries with strong administrative data. In this paper, we use new data in Guatemala and Honduras to…

Integrated data systems are often used to inform decision making at the top tiers of local or state government. Policymakers use analyses based on large numbers of integrated data system (IDS) records (from which personal identifying information has been removed) to understand the overlap between cases that receive services from different systems…

In this article, the author describes the "Be your own groundhog" project in her grades 9-12 Earth and environmental sciences courses, in which students use citizen science databases to research the physical changes that signal the arrival of spring. This project starts with a simple question, "When will spring spring?" This goes beyond the…

The purpose of this study was to determine the predictive ability of vocational rehabilitation services for deaf and hard of hearing consumers who received college and university training. The RSA-911 database for fiscal year 2004 was analyzed to evaluate the effectiveness of 21 services in leading to competitive employment. A model predicting…

Community colleges continue to experience growth in online courses. This growth reflects the need to increase the numbers of students who complete certificates or degrees. Retaining online students, not to mention assuring their success, is a challenge that must be addressed through practical institutional responses. By leveraging existing student…

Data mining of IPEDS data is used to develop models that calculate predicted graduation rates for two- and four-year institutions. (Contains 7 tables and 5 figures.)

Examined are methodologies for modeling students' choices among higher education institutions. A statistical technique called "conditional logit analysis" is applicable to the problem studied. These applications are reviewed and certain weaknesses inherent in the approach are pointed out. Alternative approaches are offered, based on the…

The major benefit of an environmental scanning/forecasting system is in providing critical information for strategic planning. Such a system allows the institution to detect social, technological, economic, and political trends and potential events. The environmental scanning database developed by United Way of America is described. (MLW)

Wesleyan University's imaginative use of computer programing helped project into the future and consider alternative fund-raising methods. The process of planning the model and its use in assessing three program options are outlined, and the computer method's usefulness in motivating development staff is emphasized. (MSE)

Predicts that, over the next several decades, technological advancements in large scale database construction and maintenance, high speed digital transmission networks, and highly precise intelligent searchware will result in a worldwide information system. A projected model illustrates pricing and retrieval rate changes that may be expected over…

This report describes the development of a teacher cost model for the Ontario secondary school system that allows educational officials, using a specified set of input information, to forecast the provincial wage-bill for a period of up to five years. The model is composed of two sub-models -- the teacher manpower sub-model and the teacher salary…

Discusses importance of academic planning and describes a model-based decision support system for academic units in a university hierarchy. This system integrates macro-level decisions by examining individual departments' budgets to determine future plans. Quantitative techniques for forecasting change are reviewed, including use of spreadsheet…