Longitudinal, Repeated Measures in Multisite Partially Nested Experiments: Estimation, Inference, and Power

• In Event: AERA Roundtable Session Saturday 11:40 am Four Seasons Ballroom 4
  In Roundtable Session: Complexity in Data: Simulations and Applications in Complex, Multivariate, Multilevel, and Nonnormal Models (Table 2)

Abstract

Repeated measures or longitudinal studies are commonly used to investigate phenomena such as individual growth trajectories, impacts of interventions over time, and critical moderators of individual change. However, they have not been well adapted to multilevel structures encountered in contemporary research, such as partially nested structures, where the treatment induces clustering that does not exist in the control condition. Most empirical studies have neglected these structures in both design and analysis. This study focuses on multisite experimental designs with repeated measures in partially nested structures. We outline the nature of this design and detail the statistical models, develop principles of estimation and inference and expressions to track statistical power, validate through simulation studies, and conclude with directions for future research.

Authors

• Yanli Xie, Florida State University

• Benjamin Kelcey, University of Cincinnati

• Wei Li, University of Florida

• Fangxing Bai, Montana State University