Rescuing Computerized Testing by Breaking Zipf's Law

Howard Wainer

Journal of Educational and Behavioral Statistics, 2000, vol. 25, issue 2, 203-224

Abstract: For many reasons, both economic and psychometric, computerized tests are typically administered continuously throughout the year rather than at only a few dates spread out over the year. Continuous test administration can yield serious security problems, since examinees could remember some of the items administered and communicate them to other potential examinees. In this essay I argue that because of the nonlinear relationship between item usage and item security, this problem cannot be resolved merely by increasing the size of the item pool. I found that, with the then current methods of exposure control, in order for an item pool's security to increase linearly the size of the pool must increase exponentially. Such a strategy is not economically feasible. In addition to offering evidence of the failure of obtaining a secure item pool merely through increases in the item pool size I provide two alternative strategies with a much better chance of success.

Keywords: item security; Poisson process; item selection algorithms (search for similar items in EconPapers)
Date: 2000
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.3102/10769986025002203 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:jedbes:v:25:y:2000:i:2:p:203-224

DOI: 10.3102/10769986025002203

Access Statistics for this article

More articles in Journal of Educational and Behavioral Statistics
Bibliographic data for series maintained by SAGE Publications ().