Analysis of cluster randomised stepped wedge trials with repeated cross-sectional samples

Karla Hemming,Monica Taljaard,Andrew Forbes

doi:10.1186/s13063-017-1833-7

Abstract

BackgroundThe stepped wedge cluster randomised trial (SW-CRT) is increasingly being used to evaluate policy or service delivery interventions. However, there is a dearth of trials literature addressing analytical approaches to the SW-CRT. Perhaps as a result, a significant number of published trials have major methodological shortcomings, including failure to adjust for secular trends at the analysis stage. Furthermore, the commonly used analytical framework proposed by Hussey and Hughes makes several assumptions.MethodsWe highlight the assumptions implicit in the basic SW-CRT analytical model proposed by Hussey and Hughes. We consider how simple modifications of the basic model, using both random and fixed effects, can be used to accommodate deviations from the underlying assumptions. We consider the implications of these modifications for the intracluster correlation coefficients. In a case study, the importance of adjusting for the secular trend is illustrated.ResultsThe basic SW-CRT model includes a fixed effect for time, implying a common underlying secular trend across steps and clusters. It also includes a single term for treatment, implying a constant shift in this trend under the treatment. When these assumptions are not realistic, simple modifications can be implemented to allow the secular trend to vary across clusters and the treatment effect to vary across clusters or time. In our case study, the naïve treatment effect estimate (adjusted for clustering but unadjusted for time) suggests a beneficial effect. However, after adjusting for the underlying secular trend, we demonstrate a reversal of the treatment effect.ConclusionDue to the inherent confounding of the treatment effect with time, analysis of a SW-CRT should always account for secular trends or risk-biased estimates of the treatment effect. Furthermore, the basic model proposed by Hussey and Hughes makes a number of important assumptions. Consideration needs to be given to the appropriate model choice at the analysis stage. We provide a Stata code to implement the proposed analyses in the illustrative case study.

Highlights

The stepped wedge cluster randomised trial (SW-Cluster randomised trial (CRT)) is increasingly being used to evaluate policy or service delivery interventions
Stepped wedge cluster randomised trials (SW-CRTs), that is, trials in which clusters are randomised to become exposed to an intervention sequentially over time [1,2,3], are rapidly increasing in popularity
The stepped wedge cluster randomised trial (SW-CRT) is appealing as it offers a means of conducting a randomised trial within a naturalistic setting

Summary

Introduction

The stepped wedge cluster randomised trial (SW-CRT) is increasingly being used to evaluate policy or service delivery interventions. A characteristic feature of this design is that the evaluation happens over an extended period of time in which the proportion of clusters exposed to the intervention gradually increases. In the early history of cluster randomised trials it was not unusual to see trial results published without allowing for clustering, yielding results which were overly precise This remained a prevalent problem for years [11,12,13]. Failure to account for time has even appeared in the recent methodological literature [15] This is potentially a greater problem than failing to adjust for clustering, as it has implications for bias as well as for precision

Objectives

Methods

Results

Discussion

Conclusion