Selecting the Best Fit Model in Cognitive Diagnostic Assessment: Differential Item Functioning Detection in the Reading Comprehension of the PhD Nationwide Admission Test

This study was an attemptto provide detailed information of the strengths and weaknesses of test takers‟ real ability through cognitive diagnostic assessment, and to detect differential item functioning in each test item. The rationale for using CDA was that it estimates an item‟s discrimination power, whereas clas- sical test theory or item response theory depicts between rather within item multi-dimensionality. To ful- fill the purpose of this study, latent attributes are shown in a Q-matrix and 4200 participants who sought to pursue their studies at the PhD level at state universities were randomly selected. The test used for the present research consisted of two different reading passages with 10 multiple-choice items consisting of four options. The data were analyzed with the application of R studio package, GDINA, and DINA mod- els. Item and model fit indices were estimated and the Wald test was run. The result of the study revealed that some items flagged DIF. The study further concluded that CDA can provide pedagogically useful diagnostic information for test designers, teachers, syllabus and materials developers, and policymakers as a proficiency test needs to be valid, reliable, and fair in the context of high-stakes tests so that it im- proves the knowledge of test takers.