Planning Mediation Studies for Interventions That Induce Partially Nested Structures

• In Event: Fancy Structural Equation Modeling and Hierarchical Linear Modeling

Abstract

Analysis of the intermediate behaviors and mechanisms through which innovative interventions and therapies come to shape outcomes is a critical objective in many areas of education and psychological research because it supports the iterative exploration, development, and refinement of theories and therapies. There is limited guidance on how to effectively and efficiently design studies to detect such mediated effects in the partially nested types of designs that commonly arise in education and psychological research. In this study, we develop statistical power formulas to identify requisite sample sizes and guide the planning of studies probing mediation under two- and three-level partially nested designs. We show how to use these results to plan a variety of studies with complex partially nested structures.

Authors

• Fangxing Bai, University of Cincinnati

• Benjamin Kelcey, University of Cincinnati

• Yanli Xie, University of Cincinnati