Two new Journal of Computerized Adaptive Testing articles
The Journal of Computerized Adaptive Testing has published two new articles. We invite you to review the article titles and abstracts below and then visit our web site to download the complete articles:
- Volume 9 No. 1, Improving Precision of CAT Measures, by John J. Barnard
The basic idea of adaptive testing is quite simple and has been implemented for over a century. Dichotomously scored multiple-choice questions are commonly used to obtain response vectors in computerized adaptive tests (CATs). A response is scored as either correct or as incorrect. However, a correct response does not necessarily mean that the examinee knew the answer. Although the standard error increasingly decreases as the provisional ability is estimated, the question is whether the process can be improved at the item response level. In other words, can more information be extracted from a response than a simple 0 or 1? Implementation of option probability theory holds promise to address this question.
- Volume 9 No. 2, The (non)Impact of Misfitting Items in Computerized Adaptive Testing, by Christine DeMars
To assess the potential impact of misfitting items, simulees received varying percentages of misfitting items. The fit was manipulated to be poor near what would otherwise be the point of maximum information. With 30% misfitting items, the absolute value of the bias of the θ estimates tended to be larger than it was with 0% or 10% misfitting items. However, the magnitude of this effect was small. For most θs and test lengths, the empirical standard error did not vary greatly with the percentage of misfitting items. The standard error estimated from the information function tended to underestimate the empirical standard error when there were 30% misfitting items, but only for higher θ levels. Overall, the misfit had little practical impact.
You can download these articles from https://jcatpub.net/index.php/jcat/issue/archive where you can also find copies of all previous JCAT articles. Other new articles, including a multiple-paper Special Issue, are in progress.
If you are currently doing research on CAT or have recently implemented a new CAT program, we would be pleased to consider a manuscript describing your work for publication in JCAT.
Thanks for the continuing interest in JCAT.
Dave Weiss
Editor Emeritus