Showing 1 - 2 of 2 Research Library Publications

Trusting Your Test Results: Building and Revising Multiple-Choice Examinations

Posted: | D. Franzen, M. Cuddy, J. S. Ilgen

Journal of Graduate Medical Education: June 2018, Vol. 10, No. 3, pp. 337-338

 

To create examinations with scores that accurately support their intended interpretation and use in a particular setting, examination writers must clearly define what the test is intended to measure (the construct). Writers must also pay careful attention to how content is sampled, how questions are constructed, and how questions perform in their unique testing contexts.1–3 This Rip Out provides guidance for test developers to ensure that scores from MCQ examinations fit their intended purpose.

Category:Assessment-Oriented Research, General Measurement

Automated Item Generation with Recurrent Neural Networks

Posted: | M. von Davier

Psychometrika 83, 847–857 (2018)

 

Utilizing algorithms to generate items in educational and psychological testing is an active area of research for obvious reasons: Test items are predominantly written by humans, in most cases by content experts who represent a limited and potentially costly resource. Using algorithms instead has the appeal to provide an unlimited resource for this crucial part of assessment development.

Category:Assessment-Oriented Research, Applications of Technology