Comparison of methods for long-range assessment in education

Abstract

There are many problems with attempting to assess the long-range impact of educational innovations or programs. The two fundamental components upon which most long-term educational evaluations are based are the use of standardized tests to measure cognitive growth and methodologies which project normal growth. Long-range educational evaluations are then based upon this notion of normal growth. This study examines the accuracy of various student test score projection techniques-idiographic analysis, standard score method, regression analysis and a differential equation growth model. The study found that even though estimates for its parameters were derived from a small sample, the differential equation growth model was generally more accurate for long-range projection than the other models and approximately the same accuracy for short-term projections as regression. Idiographic analysis and the standard score method were generally poor in terms of accuracy of prediction, especially for extended time periods. The study concludes with an overview of the problems of projecting student test scores and suggests a stochastic procedure based upon Bayesian analysis as a more realistic probabilistic projection technique for use in educational policy formulation—especially since this procedure is more compatible with expected value and benefit cost analysis which are now becoming an integral part of comprehensive instructional evaluation.