Secondary Analysis of NAEP Visual Arts Data Using Bayesian Structural Equation Modeling

• In Event: Marriott Roundtable Session 57
  In Roundtable Session: Using NAEP Data to Improve Practice and Examine Student Achievement

Abstract

Using Bayesian structural equation modeling, the study conducts a secondary analysis of the 2008 National Assessment of Educational Progress (NAEP) visual arts data (3,912 eighth graders) to investigate the associations between students’ visual art response performance and four constructs: 1) home environment, 2) personal characteristics, 3) in-school curriculum, and 4) art-related extracurricular activities. The specified model included the four constructs and a composite outcome on students’ art performance from a factor analysis of all five NAEP plausible values. In the model, as high as 38.5% of the variance in the outcome was explained by the four constructs, home environment had the strongest impact, in-school curriculum had the least, and the association between extracurricular activities and performance was negative.

Authors

• Lihua Xu, Western Carolina University

• Hongwei Yang, University of West Florida