Expanding the Meaning of Adaptive Testing to Enhance Validity
The computerized adaptive test (CAT), which adjusts the difficulty levels of administered items to match the ability levels of the test takers, has a long history of providing efficient testing. After 50 years of research, however, CATs have evolved little beyond the initial idea of adapting item difficulty. In this paper I suggest that we begin viewing adaptation in a more expanded manner, arguing that measurement will be further improved by a CAT’s being able to detect and adapt to the presence of construct-irrelevant factors that threaten the validity of individual test scores. Several examples of innovative adaptations currently provided by an operational CAT program are discussed.
Authors who publish in JCAT agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Articles may be copied and reproduced for academic and research purposes with no cost.
- All other reproduction requires permission of the author(s).
- If the authors cannot be contacted, permission can be requested from IACAT.
- Authors may enter into separate contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., publish it in a book), with an acknowledgement of its initial publication in JCAT.