Sample Size Considerations for Stepped Wedge Designs with Subclusters

October 21, 2021

IMPACT Collaboratory members Kendra Plourde, PhD, Fan Li, PhD,  and Monica Taljaard, PhD  recently co-authored an article in Biometric Methodology, Sample size considerations for stepped wedge designs with subclusters.

From the article abstract:

The article describes stepped wedge cluster randomized trial (SW-CRT), as an increasingly popular design for evaluating health service delivery or policy interventions. An essential consideration of this design is the need to account for both within-period and between-period correlations in sample size calculations. Especially when embedded in health care delivery systems, many SW-CRTs may have subclusters nested in clusters, within which outcomes are collected longitudinally. Existing sample size methods that account for between-period correlations have not allowed for multiple levels of clustering. The authors present computationally efficient sample size procedures that properly differentiate within-period and between-period intracluster correlation coefficients in SW-CRTs in the presence of subclusters. They also introduce an extended block exchangeable correlation matrix to characterize the complex dependencies of outcomes within clusters.