Designing Multilevel Mediation Experiments

• In Event: Propensity Scores and Causal Inferences

Abstract

The purpose of this study was to develop a flexible framework to guide the statistical design of multilevel mediation experiments. Despite the consistent presence of mediation models in the theories of action underlying most studies in education, literature has not derived and developed the statistical formulas necessary to assess power and guide sample size determination in studies that examine multilevel mediation. In this study, we derive and develop statistical formulas for power under a wide range of design considerations. The framework is implemented in the R library BLINDED and the free BLINDED software.

Author

• Benjamin Kelcey, University of Cincinnati