Moving to the Next Level With Doubly Latent Multilevel Mediation Models in School Climate Research

• In Event: AERA Poster Session 7
  In Poster Session: Division D Section 2 Poster Session 2

Abstract

Traditional multilevel models for evaluating indirect effects are limited by their inability to quantify measurement and sampling error resulting from the sampling of observed variables and persons within level two units, respectively. They are further restricted by being unable to fully separate within- and between-level effects without bias. Doubly latent multilevel mediation models reduce these biases by decomposing the observed within-level indicators into within- and between-level latent components. We illustrate this approach in investigating the mediating role of engagement in associations between school climate and a variety of student outcomes, in a statewide high school sample of 59,581 students and 11,336 teachers from 296 schools. Substantive findings reveal that student engagement mediates relationships between school climate factors and student outcomes.

Authors

• Yuane Jia, Rutgers University

• Timothy R. Konold, University of Virginia