Answers are grounded in this paper and cite their sources.
This study examines the effect of altering test difficulty on examinee ability measures and test length in a computer adaptive test. The participating 225 examinees were randomly assigned to three test difficulty conditions and given a variable length computer adaptive test. Examinees in the hard, medium, and easy test conditions took a test targeted at the SO%, 60%, or 70% probability of correct response. The results show that altering the probability of a correct response does not affect estimation of examinee ability and that taking an easier computer adaptive test only slightly increases the number of items necessary to reach specified levels of precision.
No takes yet. Share an insight, caveat, or question.
Bergstrom et al. (1992) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: