A Multilevel Latent Variable Approach to Estimating Rater Effects: An Illustration With School Climate Data

• In Event: AERA Poster Session 4
  In Poster Session: Division D Section 2 Poster Session 1

Abstract

Measuring and understanding the nature of informant differences (Level 1) when the target of measurement is at the organizational level (Level 2) involves a number of methodological considerations. These issues are described in the context of specifying a correlated trait – correlated method minus one (CT–C(M-1); Koch et al., 2015) latent model for multilevel applications. The approach allows for evaluating many possible differences between structurally different informant ratings of a common trait. The modeling approach and various facets of interpretation are described in the context of an illustration in which student (N = 58,018), teacher (N = 12,236), and health professional (N = 742) reports were used to gauge school climate in 294 high schools.

Authors

• Timothy R. Konold, University of Virginia

• Elizabeth A. Sanders, University of Washington