Explores whether flexible nonlinear models (including neural networks and genetic algorithms) can reveal otherwise unexpected patterns of relationship in typical school-productivity data. Applying three types of algorithms alongside regression modeling to school-level data in 183 elementary schools proves the hypothesis and reveals new directions…

Applies neural network methods for forecasting 1991-95 per-pupil expenditures in U.S. public elementary and secondary schools. Forecasting models included the National Center for Education Statistics' multivariate regression model and three neural architectures. Regarding prediction accuracy, neural network results were comparable or superior to…

Describes how to employ multivariate regression models and National Research Council data (used to rank doctoral programs) to analyze how measures of program size, faculty seniority, and faculty research and doctoral-degree productivity influence subjective ratings of doctoral programs in 35 academic fields. Illustrates how to compute the effects…

College-preference studies can help administrators identify a potential pool of desirable students and implement new recruitment techniques. This study, which supports earlier findings, used a logistic regression model to investigate the effects of variables relating student characteristics and institutional factors on the decision to apply to a…

Investigates the effect of state and federal grants on South Carolina local revenues for 1978 and 1982. Although local revenues are stimulated by federal aid, some of the latter is used for tax relief. (MLF)

Presents a decomposition technique for a Tobit regression model that shows the effect of the independent variables on (1) the amount of financial-aid awards to those receiving aid; and (2) the probability of receiving aid for those who did not receive aid. Contributes to a clearer understanding of the effects of selected factors on awards. (20…