Optimal Sequential Rules for Computer-Based Instruction

Hans J. Vos
Journal of Educational Computing Research, Vol 19 No 2, 1998, p. 133-154

The purpose of this article is to formulate sequential rules for adapting the appropriate amount of instruction to learning needs in the context of computer-based instruction. The framework for the approach is derived from Bayesian decision theory. Both a threshold and linear utility structure are considered. The binomial distribution as well as Kelley's regression line from classical test theory are adopted as the psychometric model involved. Optimal sequential rules will be derived both for the situation that collateral information but no prior knowledge about student's true level of functioning is available and for the situation that a beta distribution representing student's prior knowledge is assumed. An empirical example of sequential instructional decision making for concept-learning in medicine concludes the article.

We hope you found what you needed on this page. If you have any questions or comments, please contact me.

Howard J. Bender, Ph.D.
President
The Education Process Improvement Center, Inc.
P.O. Box 186
Riverdale, Maryland 20738
hjbender@epicent.com