This document reports on a study that explored the feasibility of using New York State Education Department data to develop multiple regression equations required for simulating the effects of alternative expenditure configurations on pupil achievement. Specific study objectives were: (1) to test the effectiveness of factor analysis as a procedure for reducing the number of variables required as independent terms in regression equations; (2) to develop a series of equations for predicting academic achievement, given pertinent information about conditions that might affect output; (3) to evaluate the desirability of using curvilinear, rather than linear, prediction equations; and (4) to explore the feasibility of using existing data to develop equations for predicting the effects of program changes on program outputs. The study produced eight equations for estimating various dimensions of school district output. Appendixes include a catalog of information elements, conclusions based on correlation data, and application of the models. (Author/LLR)