The Continuous Response Model With Random Effect for Modeling Subjective Judgment in Rating Scale Items

• In Event: Roundtable Session 28
  In Roundtable Session: How Reliable Are Raters?

Abstract

For a test with rating scale items, not only examinees’ latent traits but also subjective judgments of the scoring rubrics have effects on responding items. The ignorance of examinees’ subjective judgments tends to affect the model-data fitting and results in a decrease in the measurement precision. To model the effect of examinees’ subjective judgments in the continuous response model (CRM; Samejima, 1973), this study extended CRM to the random effect continuous response model (RECRM). Through a simulation study, the results indicated that RECRM could recover item parameters fairly well. RECRM also showed flexibility in fitting item responses in a real data analysis. RECRM was recommended for practical applications in educational and psychological testing.

Authors

• Jyun-Hong Chen, National Chung Cheng University

• Ching-Lin Shih, National Sun Yat-sen Universit

• Shu-Ying Chen, National Chung Cheng University