Validating a Performance Assessment of Computational Thinking for Early Childhood Using Item Response Theory

• In Event: Technology and Young Children

Abstract

Despite growing interest in early childhood computational thinking (CT), there is a lack of validated assessments for children who are pre-literate or emerging readers. This paper presents validity and reliability evidence of a performance assessment of CT using item response theory (IRT) from 272 children aged 4-8. Using a two-parameter logistic model, we confirmed that model- and item-level fits are acceptable. Item analyses revealed a high discriminability and a moderate item difficulty, on average, across 19 items. Differential item functioning (DIF) analyses indicated that the assessment measured children’s latent ability of CT equally, regardless of their gender and age. Findings suggest our assessment is a fair measure that can serve as a diagnostic tool to assess early childhood CT.

Authors

• Chungsoo Na, Utah State University
  Presenting Author

• Jody E. Clarke-Midura, Utah State University
  Non-Presenting Author

• Deborah Silvis, SUNY - College at Cortland
  Non-Presenting Author

• Katelyn Ann Childers, Utah State University
  Non-Presenting Author

• Jessica F. Shumway, Utah State University
  Non-Presenting Author

• Victor R. Lee, Stanford University
  Non-Presenting Author