Practical Issues in Large-Scale High-Stakes Computerized Adaptive Testing.Report as inadecuate

Practical Issues in Large-Scale High-Stakes Computerized Adaptive Testing. - Download this document for free, or read online. Document in PDF available to download.

Computerized adaptive testing (CAT), while well-grounded in psychometric theory, has had few large-scale applications for high-stakes, secure tests in the past. This is now changing as the cost of computing has declined rapidly. As is always true where theory is translated into practice, many practical issues arise. This paper discusses a number of such issues and outlines potential problems and potential solutions. The purpose is to encourage further development of solutions to these and other practical issues facing measurement professionals involved in CAT implementation. Practical issues explored include: (1) establishing test designs through simulation studies; (2) selecting the first item; (3) choosing the stopping rule; (4) scoring adaptive tests; (5) incorporating the test plan; (6) administering items belonging to sets; (7) facilitating item ordering; (8) controlling item exposure; (9) controlling item overlap; (10) providing item review; (11) dealing with item omissions; (12) allowing for incomplete tests; (13) establishing comparability; (14) developing CAT pools; (15) maintaining CAT pools; (16) developing and prototyping new item types; (17) complying with disclosure requirements; and (18) accommodating low-volume tests. (Contains 19 references.) (Author/SLD)

Descriptors: Adaptive Testing, Computer Assisted Testing, High Stakes Tests, Item Banks, Psychometrics, Scoring, Selection, Simulation, Test Construction, Test Items, Testing Problems, Theory Practice Relationship

Author: Mills, Craig N.; Stocking, Martha L.


Related documents