| Popis: |
Score validity can be examined at both the score level and the individual level because the test score is not only a function of the items or stimuli, but is also influenced by the respondent's specifications. It is the responsibility of the test user to identify individuals who do not fit the basic model or who respond differently from the rest of the sample group. Checking the validity of the test results at the individual level can be done through a person-fit analysis. Misfit individuals can bias model results at both the test and item levels. Given the importance of detecting aberrant responses, the purpose of this study was to examine the effect of aberrant responses on item response theory-based model estimates. This study is a descriptive research and simulated data were used. For this purpose, data were collected from 1104 university students enrolled in 8 different universities in Turkey using Generalized Anxiety Disorder -7 scale. After parameter estimation based on the item response theory model, 100 different datasets were simulated using the item and person parameters obtained from these estimations. By this way, it was aimed to increase the generalizability of the findings obtained. The data were analyzed with R program using "PerFit" and "mirt" packages. Misfit persons were identified with Lz, U3, G and norm-based G person fit statistics. The findings showed that misfit persons had an effect on the model fit statistics, item fit statistics, item discrimination values, the amount of information provided by the items, the total amount of information provided by the scale, and empirical reliability levels across different levels of ability trait. In addition, in order to improve the results based on the item response theory, it was observed that removing the misfit persons detected based on the Lz technique from the dataset was the least effective among the existing techniques. On the other hand, G fit statistic has been identified as the most effective technique. The obtained results should be interpreted with caution because the simulated data was used in this study which are based on parameters representing the dataset collected with a measurement tool aimed at measuring anxiety, and these results may not be generalizable to the measurement of different traits. |
