Three-Level School-Randomized Studies Probing Mediation: Statistical Power and Requisite Sample Size

• In Event: Advanced Structural Equation Modeling and Hierarchical Modeling at Roundtable

Abstract

The purpose of our study is to develop closed-form expressions to estimate the statistical power to detect mediation effects in three-level school-randomized studies. The results provide a set of formulas and software tools that guide researchers in the planning multilevel studies incorporating mediation. We extend tests of mediation that can be used both in the planning and analysis phases including the asymptotic Sobel test, component-wise joint test, the resampling-based Monte Carlo interval test, and the partial posterior predictive distribution test.

Authors

• Yanli Xie, University of Cincinnati

• Benjamin Kelcey, University of Cincinnati

• Fangxing Bai, University of Cincinnati