A Fortran Program for Simulating Educational Growth With Varying School Impact

Abstract

To facilitate empirical investigations of longitudinal methodology, a computer procedure was developed to generate artificial data in which true growth scores are known. This procedure simulates the results of the Educational Testing Service Growth Study that pertain to the relationships among scores on a test of academic potential and scores on a test of educational attainment administered on four occasions. Similarly, the procedure simulates the results of Project TALENT that pertain to the correlation of community per capita income with average academic potential of students and with school resources. It is also assumed in the program that school resources determine school impact. The program user is allowed to specify the correlation between resources and impact and the extent to which schools vary in impact. Student scores and school means generated by this program are entered on separate output tapes.

Get full access to this article

View all access options for this article.

References

Cronbach, L. J. and Furby, L.

How should we measure change—or should we?

Psychological Bulletin, 1970, 74, 68-80.

Flanagan, J. C. , Dailey, J. T. , Shaycroft, M. F. , Orr, D. B. , and Goldberg, I. Studies of the American High School. Project TALENT Monograph No. 2. Pittsburgh: University of Pittsburgh, 1962.

Hilton, T. L. , Beaton, A. E. , and Bower, C. P. Stability and instability in academic growth—A compilation of longitudinal data. Princeton: Educational Testing Service, 1971.

Richards, J. M., Jr. A simulation study comparing procedures for assessing individual educational growth. Baltimore: Center for Social Organization of Schools, The Johns Hopkins University, 1974.