Structuring Subjective Task Value: A Comparison of Correlated-Factors, Higher-Order, and Bifactor Models

• In Event: AERA Poster Session Saturday 3:45 pm
  In Invited Poster Session: Division D Graduate Student In-Progress Research Poster Session

Abstract

Situated expectancy-value theory conceptualizes subjective task value as a multidimensional construct; however, prior research has proposed multiple competing structural representations of its components. The present study compared alternative confirmatory factor analysis, exploratory structural equation modeling (ESEM), and Set-ESEM modeling approaches for subjective task value to evaluate which representation best fits the empirical data. Survey data were collected from 498 undergraduate students enrolled in introductory mathematics and science courses. Three sets of models were estimated, including correlated-factors, higher-order, and bifactor representations. The results highlight the importance of systematically comparing alternative measurement models when operationalizing subjective task value in expectancy-value research.

Authors

• Qingqing Zhou, University of Illinois at Urbana-Champaign

• Jessica R. Gladstone, University of Illinois at Urbana-Champaign