Power to Detect Moderated Effects in Three-Level Partially Nested Designs

• In Event: Innovations in Experimental Design and Causal Inference

Abstract

Comprehensive evaluation of treatment effects is aided by considerations for moderated effects. In educational research, the combination of natural hierarchical structures and prevalence of group-administered or shared facilitator treatments often produces three-level partially nested data structures. While literature details planning strategies for a variety of experimental designs when moderation effects are of interest, power formulas for detecting moderation effects in three-level partially nested designs have yet to be established. The purpose of this study is to develop these power formulas then investigate results under common conditions to provide guidance and recommendations for study planning. Results demonstrate formula accuracy and show partially nested studies with three-levels that consider moderated effects are feasible with sample sizes seen in educational experiments.

Authors

• Kyle T. Cox, University of North Carolina - Charlotte

• Benjamin Kelcey, University of Cincinnati

• Fangxing Bai, University of Cincinnati

• Hannah Luce, University of North Carolina - Charlotte