Under given conditions, conventional testing and computer-generated repeatable testing (CGRT) are equally effective for estimating examinee ability; CGRT is more effective than conventional testing for estimating the mean ability level of a group; and CGRT is less effective for estimating ability differences among individuals. These conclusions are drawn from domain-referenced test theory as distinguished from norm-referenced test theory.
Get full access to this article
View all access options for this article.
References
1.
Baker, F.B.The role of statistics. In G. Lippey (Ed.), Computer-assisted test construction. Englewood Cliffs, NJ: Educational Technology Publications , 1974.
2.
Cronbach, L.J., Gleser, G.C., Nanda, H., & Rajaratnam, N.The dependability of behavioral measurements: Theory of generalizability for scores and profiles. New York: Wiley, 1972.
3.
Emerson, P.L.Experience with computer generation and scoring of tests for a large class . Educational and Psychological Measurement, 1974, 34, 703-709.
4.
Lippey, G. (Ed.). Computer-assisted test construction . Englewood Cliffs, N.J: Educational Technology Publications, 1974.
5.
Lord, F.M., & Novick, M.R.Statistical theories of mental test scores. Reading, MA : Addison-Wesley, 1968.
6.
Millman, J.Criterion-referenced measurement. In W. J. Popham (Ed.), Evaluation in education. Berkeley, CA: McCutchan, 1974.
