|
|
|
Wilco H.M. Emons Detection and diagnosis of misfitting item-score vectors |
|||
| |||
|
In individual decision-making in education, psychology, and personnel selection, it is critically important that test users can have confidence in the test scores used. The validity of individual test scores may be threatened when the respondent's answers are governed by factors other than the psychological trait of interest. Person-fit methods are used to detect item-score vectors that are unlikely given the test-theory model that describes the data and, as a result, may indicate an invalid measurement. This book presents new developments in person-fit methods for detection and diagnosis of misfitting item-score vectors in the context of nonparametric item-response theory. Sampling properties of several person-fit statistics are examined. Person-fit approaches are developed that can be used to diagnose possible explanations of misfit. A comprehensive person-fit methodology is presented that combines existing and newly developed person-fit methods. Real data examples from a child intelligence test are discussed. Wilco Emons (1973) studied Educational Technology at the University of Twente, majoring in Educational Measurement and Data Analysis. Currently he has a post-doctoral research position at Tilburg University. Bestel/Order |
|||
