Use of the stepped wedge design cannot be recommended: A critical appraisal and comparison with the classic cluster randomized controlled trial design

Kotz, Daniel; Spigt, Mark; Arts, Ilja C. W.; Crutzen, Rik; Viechtbauer, Wolfgang

doi:10.1016/j.jclinepi.2012.06.004

Cited by 76 publications

(78 citation statements)

References 5 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach can inform the choice between any two candidate designs: for example, that between a stepped‐wedge and parallel design 14, 16, 17, 18, 19, 20, 21, 22. From (4) the stepped‐wedge is the more efficient only if R > r 0 where the threshold r 0 satisfies

a_{S W} - b_{S W} r_{0} = a_{P D} - b_{P D} r_{0} .

…”

Section: The Precision Of the Effect Estimate Under A Linear Mixed Efmentioning

confidence: 99%

Statistical efficiency and optimal design for stepped cluster studies under linear mixed effects models

Girling

Hemming

2016

Statistics in Medicine

111

266

View full text Add to dashboard Cite

In stepped cluster designs the intervention is introduced into some (or all) clusters at different times and persists until the end of the study. Instances include traditional parallel cluster designs and the more recent stepped‐wedge designs. We consider the precision offered by such designs under mixed‐effects models with fixed time and random subject and cluster effects (including interactions with time), and explore the optimal choice of uptake times. The results apply both to cross‐sectional studies where new subjects are observed at each time‐point, and longitudinal studies with repeat observations on the same subjects.The efficiency of the design is expressed in terms of a ‘cluster‐mean correlation’ which carries information about the dependency‐structure of the data, and two design coefficients which reflect the pattern of uptake‐times. In cross‐sectional studies the cluster‐mean correlation combines information about the cluster‐size and the intra‐cluster correlation coefficient. A formula is given for the ‘design effect’ in both cross‐sectional and longitudinal studies.An algorithm for optimising the choice of uptake times is described and specific results obtained for the best balanced stepped designs. In large studies we show that the best design is a hybrid mixture of parallel and stepped‐wedge components, with the proportion of stepped wedge clusters equal to the cluster‐mean correlation. The impact of prior uncertainty in the cluster‐mean correlation is considered by simulation. Some specific hybrid designs are proposed for consideration when the cluster‐mean correlation cannot be reliably estimated, using a minimax principle to ensure acceptable performance across the whole range of unknown values. © 2016 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

show abstract

a_{S W} - b_{S W} r_{0} = a_{P D} - b_{P D} r_{0} .

…”

Section: The Precision Of the Effect Estimate Under A Linear Mixed Efmentioning

confidence: 99%

Statistical efficiency and optimal design for stepped cluster studies under linear mixed effects models

Girling

Hemming

2016

Statistics in Medicine

111

266

View full text Add to dashboard Cite

show abstract

“…We also explained that rolling out the intervention to control clusters after the final data collection will result in a shorter duration to conduct a cluster RCT and, in addition, has the advantage that the intervention will only be rolled out if proven to be effective [2]. The repeated measurement of data from all clusters at each step, which is the key characteristic that differentiates the SWD from the cluster RCT, has two very important drawbacks: it puts a heavy burden on patients, caregivers, and researchers, and increases the risk of contamination and attrition [2]. Thus, in our opinion, the SWD should therefore only be considered in the absence of these two drawbacks.…”

mentioning

confidence: 99%

“…We thank Mdege et al [1] for their response to our critical appraisal [2] of the stepped wedge design (SWD). They agree with us that the SWD has many disadvantages compared with the cluster randomized controlled trial (cluster RCT) and that the cluster RCT is preferable in most circumstances.…”

mentioning

confidence: 99%

Researchers should convince policy makers to perform a classic cluster randomized controlled trial instead of a stepped wedge design when an intervention is rolled out

Kotz¹,

Spigt²,

Arts³

et al. 2012

Journal of Clinical Epidemiology

Self Cite

View full text Add to dashboard Cite

We thank Mdege et al. [1] for their response to our critical appraisal [2] of the stepped wedge design (SWD). They agree with us that the SWD has many disadvantages compared with the cluster randomized controlled trial (cluster RCT) and that the cluster RCT is preferable in most circumstances. However, they also maintain that the SWD may be useful when the alternative is to conduct no randomized trial at all and that some of the cluster RCT variants that we suggest in our article are in fact variants of the SWD. To clarify the latter and better understand the discussion about the advantages and disadvantages of the SWD compared with the cluster RCT, it is important to point out the key difference between the two designs.So, what actually differentiates the SWD from the cluster RCT? In our view, it is the repeated measurement of data from all clusters at each step. As we explained in our critical appraisal, other features of the SWD are not unique to this design but can also be part of a cluster RCT: rolling out an intervention to all clusters and sequential implementation of the intervention [2]. We also explained that rolling out the intervention to control clusters after the final data collection will result in a shorter duration to conduct a cluster RCT and, in addition, has the advantage that the intervention will only be rolled out if proven to be effective [2]. The repeated measurement of data from all clusters at each step, which is the key characteristic that differentiates the SWD from the cluster RCT, has two very important drawbacks: it puts a heavy burden on patients, caregivers, and researchers, and increases the risk of contamination and attrition [2]. Thus, in our opinion, the SWD should therefore only be considered in the absence of these two drawbacks.Then when can the SWD be used instead of the cluster RCT? We agree with Mdege et al. that the SWD could be applied under some circumstances. However, the set of circumstances in which the SWD may be the preferred alternative (i.e., in the absence of the two aforementioned drawbacks) are rather limited. For one thing, all necessary data must be routinely collected at the appropriate time intervals (i.e., at the inclusion of each additional cluster) and in a reliable and valid fashion without additional burden for patients, caregivers, and researchers. Unfortunately, situations in which this applies are rather exceptional, which in our opinion severely limits the applicability of the SWD. Often, the routine collection of data is incomplete and not all necessary data are collected (in particular relevant covariates).There may be one other situation in which the SWD may be preferable to a cluster RCT: when the number of clusters is extremely low and the researcher has no control over the number of clusters. In both designs, the power increases much more with an increasing number of clusters than with

show abstract

“…These challenges are firstly that larger sample sizes might be required for some outcomes since, with the increased number of groups to compare, the design may have less statistical power than the regular (cluster) RCT (28,29). Secondly, the data collection in each time period can put a high burden on participants and researchers, which might hamper the feasibility of the study (29). The design is most feasible if data can be (partly) routinely collected at the appropriate time intervals in a reliable and valid way (28).…”

Section: Alternative Design In Experimental Researchmentioning

confidence: 99%

Evaluation of occupational health interventions using a randomized controlled trial: challenges and alternative research designs

Schelvis¹,

Hengel²,

Burdorf³

et al. 2015

Scand J Work Environ Health

100

104

View full text Add to dashboard Cite

This overview aims to guide researchers in occupational health in conducting evaluative research. Several appropriate alternatives for the randomized controlled trial design are available and feasible (ie, stepped wedge, propensity scores, instrumental variables, multiple baseline design, interrupted time series, difference-in-difference, and regression discontinuity), which may provide sufficiently strong evidence to guide decisions on implementation of interventions in workplaces.Affiliation:

show abstract

Use of the stepped wedge design cannot be recommended: A critical appraisal and comparison with the classic cluster randomized controlled trial design

Cited by 76 publications

References 5 publications

Statistical efficiency and optimal design for stepped cluster studies under linear mixed effects models

Statistical efficiency and optimal design for stepped cluster studies under linear mixed effects models

Researchers should convince policy makers to perform a classic cluster randomized controlled trial instead of a stepped wedge design when an intervention is rolled out

Evaluation of occupational health interventions using a randomized controlled trial: challenges and alternative research designs

Contact Info

Product

Resources

About