ERIC Number: ED224831
Record Type: RIE
Publication Date: 1982-Nov
Reference Count: 0
Latent Trait Models for Answer-Until-Correct Tests. Methodology Project.
The answer-until-correct procedure has made comparatively little impact on the field of educational testing due to the absence of a sound theoretical base for turning the response data into measures. Three new latent trait models are described. They differ in their complexity, though each is designed to yield a single parameter to measure student achievement. The simplest, a "partial credit" model, has a single difficulty parameter for each item. This model takes no account of the variations in distractor attractiveness from item to item, nor of which distractors were actually selected by the respondent. The second model treats the test as a sequence of distinct steps, each of which has a difficulty parameter. This method does not assume that all items have the same logical structure with regard to difficulty. It takes no account of which distractors are selected. The third model is an extension of the second. In this model, the step difficulty values for an item vary in terms of which distractors were previously selected. A technical manual describing software developed for an effective and efficient program for administering answer-until-correct tests using microcomputer systems is reported as Appendix 1. (Author/PN)
Publication Type: Reports - Research
Education Level: N/A
Sponsor: National Inst. of Education (ED), Washington, DC.
Authoring Institution: California Univ., Los Angeles. Center for the Study of Evaluation.
Identifiers: Answer Until Correct; Rasch Model