Investigating Factor Structure and Method Effects of the PISA (Programme for International Student Assessment) Perceived Control Scale

• In Event: Roundtable Session 46
  In Roundtable Session: Applications of Factor Analysis and Structural Equation Modeling

Abstract

Method effects associated with negatively worded items in attitude questionnaires have been found to generate systematic measurement errors. Using a sample of 3,190 US students from PISA 2012 dataset, this study evaluates whether method effects are present on the Perceived Control scale. Confirmatory factor analysis (CFA) was used to compare three models: a single factor model, a two-factor model, and a Correlated trait and Correlated Methods (CTCM) model (DiStefano & Motl, 2006). Among models tested, the CTCM model was the most consistent with the data and suggested method effects associated with negatively worded items need to be considered in the latent construct.

Authors

• Breanna Morrison, University of Arkansas

• Wen-Juo Lo, University of Arkansas

• Ronna L. Turner, University of Arkansas

• Lihua Yang, University of Arkansas

• Sho-Hsien Su, University of Arkansas at Fayetteville