ERIC Number: ED159200
Record Type: RIE
Publication Date: 1978-Mar
Reference Count: 0
A Live Tailored Testing Comparison Study of the One and Three Parameter Logistic Models.
Koch, Bill R.; Reckase, Mark D.
A live tailored testing study was conducted to compare the results of using either the one-parameter logistic model or the three-parameter logistic model to measure the performance of college students on multiple choice vocabulary items. The results of the study showed the three-parameter tailored testing procedure to be superior to the one-parameter procedure on the basis of goodness of fit of observed to predicted item responses, test-retest reliability, convergence to stable ability estimates, and test information. No differences were found in the prediction of an outside criterion. However, implicit in these results was the assumption that the nonconvergence problem encountered in one-third of the cases for the three-parameter procedure could be solved. Thus, based on the data reported in this study, the three-parameter tailored testing method was deemed the technique of choice, at least for unidimensional tests consisting of multiple choice items where guessing is a factor. (Author)
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: N/A
Identifiers: Latent Trait Models; Rasch Model; Three Parameter Model
Note: Paper presented at the Annual Meeting of the American Educational Research Association (62nd, Toronto, Ontario, Canada, March 27-31, 1978)