Sample size and power calculation stepped wedged design. A simulation study of statistical approaches to data analysis in the stepped wedge design. This article introduces the stata menudriven program steppedwedge, which. I am looking for an advice on sample size and power calculation for an intervention study. Design and analysis of cluster randomization trials in health. While analytic approaches for power calculations do exist in the context of this complex study design, it seemed worth the effort to be explicit about all of the.
Below is the programming figure 2 which is used for the simulation using the do loop. Conducting a power analysis there many software products available for performing a power analysis, some of. Sample size and power in prospective analysis of relative risk. Quasiexperimental designs in practicebased research. Upgrade at the online store we are pleased to announce the release of pass 2020. Stepped wedge designs are useful for phase iv trials, to evaluate the effect of time on the intervention, and as a way of dealing with logistic difficulties of implementing the intervention everywhere at once power is relatively insensitive to cv maximize the number of steps.
In their seminal article on stepped wedge studies, hussey and hughes derive a method of estimating the power available from an swcrt. Power analysis of trials with multilevel data 1st edition. Using the stepped wedge cluster design we will analyse the differences between prenetworkz and postnetworkz cohorts on each of the patient outcome measures. Stepped wedge designs offer a number of opportunities for data analysis, particularly for modelling the effect of time on the effectiveness of an intervention. It anticipates coming problems and quickly finds the root causes. The study aims to evaluate the effectiveness of case managers intervention in improving linkage and retention rates to hiv care among newly diagnosed hivinfected persons. Tests for two proportions in a steppedwedge clusterrandomized. Second, there is possibly additional clustering at the patient level since individual outcomes. Aug 17, 2015 stepped wedge cluster randomised trials introduce interventions to groups of clusters in a random order and have been used to evaluate interventions for health and wellbeing. There are relatively simple and accessible methods to allow for design complexities such as variable cluster sizes. Keener, phd university of pittsburgh, 2018 a stepped wedge trial is a type of cluster randomized trial with unidirectional crossover from control to intervention. Power and sample size determination for stepped wedge. The reporting and analysis of swts pose many of the same.
Power and sample size determination for stepped wedge cluster. Apr 16, 2020 the analysis software will include methods to identify outlying data elements cluster, period, or cluster period with large influence on study results, to establish robustness as well as statistical options for finitesample bias corrections to account for the small numbers of clusters common to stepped wedge trials. Among the new procedures are those for groupsequential tests, gee tests, confidence intervals for cluster andor stratified designs, postmarketing surveillance. For cohort stepped wedge designs there was only one paper considering analysis and one considering sample size methods. Hakhu, and emily voldal description a set of tools for examining the design and analysis aspects of stepped wedge cluster ran. Interrupted time series power calculation using do loop.
Although the stepped wedge design extends the length of a randomized trial due to the presence of multiple time intervals, the nature of the design may be beneficial in certain settings. Power analysis of trials with multilevel data covers using power and sample size calculations to design trials that involve nested data structures. Stepped wedge design the stepped wedge design is a pragmatic study design which can reconcile the need for robust evaluations with political or logistical constraints. Package swcrtdesign october 25, 2019 type package title stepped wedge cluster randomized trial sw crt design version 3. Jiachen chen software of power calculations for stepped wedge design with binary outcomes. The specific features of swts need to be addressed properly.
Methods and analysis the study is a prospective, stepped wedge cluster randomised trial with crosssectional exposure and outcome measurement via retrospective database analysis of administrative records. Feasibility of a stepped wedge cluster rct and concurrent observational substudy to evaluate the effects of modified ward night lighting on inpatient fall rates and sleep quality. This design is proposed for a future trial that aims to study the effectiveness of a population health management phm intervention based on electronic health record ehr among patients. Certainly its performance improves on that of the simple parallel study if the intracluster correlation is large. The chapters correspond to the procedures available in pass. Since a logrank test statistic for intervention effect calculated for a simulated stepped wedge trial z sw will generally always be lower than the corresponding statistic z e for a parallel group trial, because allocation ratios of patients to intervention or control status for parallel group trials remain equal while for stepped wedge. In a stepped wedge design, however, the clusters switch or cross over in one direction only usually from the control group to the treatment group. Robust analysis of stepped wedge trials using cluster. In the stepped wedge design, all clusters in a trial will receive the intervention at some point, but the start of the intervention will be staggered. An analysis which assumes a homogeneous intervention effect across clusters may be biased heterogeneity can reduce power 21 hughes jp, granston ts, heagerty pj. Please contact the technology and analysis core for an individual consultation in designing your pilot study and planning your analysis. Design and analysis of stepped wedge cluster randomized trials. It indicates that it is loaded but i dont know how to access it in stata. Power and sample size determination for stepped wedge cluster randomized trials christopher m.
Swsamp simulationbased sample size calculations for a stepped wedge trial and more swsamp is an r package designed to allow a wide range of simulationbased sample size calculations, specifically but not exclusively. Design and analysis of stepped wedge cluster randomized trials michael a. Unit of analysis a key property of cluster randomization trials is that inferences are frequently intended to apply at the individual level while randomization is at the cluster or group level. To this extent, it combines features of both the stepped wedge and the parallel design. Stepped wedge trials swt is a special type of crossover cluster randomized trials crt in which clusters are randomized to initiate treatment at different points in time. Tests for two means from a clusterrandomized design. Methods that determine statistical power for a stepped wedge trial of fixed size4 20 21 have been implemented in the statistical software package stata. Analysing an open cohort steppedwedge clustered trial. A steppedwedge clusterrandomized design is similar to a crossover design in that each cluster. We found that a stepped wedge trial with an equal allocation to sequences is optimised by obtaining all observations after the first sequence switches and before the final sequence switches to the intervention. Thus the unit of randomization may be different from the unit of analysis. All the analysis in this paper was done using sas enterprise guide software version 6.
Mixed effects approach to the analysis of the stepped wedge. We aim to provide an analytical formula for power analysis under this situation to aid the stepped wedge. Analytical methods for sample size calculations in a stepped wedge trial. Design and analysis of cluster randomization trials in. Whether you work in production management, process and product development, quality management, maintenance, process control, or mill management, wedge. Strengths and weaknesses of a stepped wedge cluster. Survival analysis 2 group comparison with preliminary data 53. In a stepped wedge cluster design, the randomization unit is still the group, but all groups are eventually exposed to the intervention at some point in the study. Aug 27, 2018 i am going to walk through the data generation process for each of the variations and then present the results of a series of power analyses to compare and contrast each design.
Design and analysis of stepped wedge cluster randomized. The stepped wedge design requires a substantial smaller sample size than a. We also found that the approximate weighted least square approach of hussey and hughes 2007, design and analysis of stepped wedge cluster randomized trials. Power was assessed by simulations for stepped wedge trials with a uniform intra cluster correlation of 0. Analysis was conducted on an intention to treat basis, operationalised within a stepped wedge design as analysed according to the allocated crossover time, irrespective of whether that was achieved. Because the stepped wedge design uses both withincluster and betweencluster information, power is relatively insensitive to variations in the cv. This data step creates scenarios in which the following parameters are varied. Swsamp is a general purpose package to provide a suite of functions for the sample size calculations and power analysis in a stepped wedge trial.
The amount of time in each state control or intervention will differ for each site or group of sites if there are waves of more than one site starting up at the same time. Power analysis for stepped wedge trials with delayed. University of birmingham the stepped wedge trial design. We find that gee models with exchangeable correlation structures are more efficient than gee. The stepped wedge cluster randomised controlled trial design swt has been used to evaluate interventions to improve health, as well as other aspects of wellbeing. Features of powerful processanalytics software trimble. I found and downloaded the step wedge power package. Sample size calculation for stepped wedge and other.
Implementation of a pragmatic, steppedwedge cluster. Aug 17, 2015 stepped wedge trials swts can be considered as a variant of a clustered randomised trial, although in many ways they embed additional complications from the point of view of statistical design and analysis. A simulation study of statistical approaches to data. In section 3, we describe the imple mentation of simulation based power analysis on. A steppedwedge trial or swt is a type of randomised controlled trial or rct, a scientific experiment which is structured to reduce bias when testing new medical treatments, social interventions, or other testable hypotheses. In section 7, we discuss an r program that will be released to compute sample size and power for stepped wedge trials. The stepped wedge design increased the complexity of the data analysis, and there were concerns regarding the informed consent procedure.
I am going to walk through the data generation process for each of the variations and then present the results of a series of power analyses to compare and contrast each design. A few factors make this analysis particularly interesting. An example of the logistics of a stepped wedge trial design is shown in figure 1, which shows a stepped wedge design with five steps. Testing the use of practice facilitation in a cluster. Sample size calculations for stepped wedge and cluster. The use of a stepped wedge design offers several advantages, such as the possibility of betweenand withingroup analyses, increased study power. In a parallel or traditional crossover design, the intervention must be implemented in half of the total clusters simultaneously. By the end of the study, all participants will have received the intervention, although the order in which participants receive the intervention is determined at random. Our method covers both standard steppedwedge designs i.
We assign the intervention using a clusterlevel balanced randomisation scheme based on. Analysis and reporting of stepped wedge randomised. Evaluation of the impact of an augmented model of the. I am currently wrestling with how to analyze data from a stepped wedge designed cluster randomized trial. Stepped wedge trials swts can be considered as a variant of a clustered randomised trial, although in many ways they embed additional complications from the point of view of statistical design and analysis. Data analysis to determine the overall effectiveness.
A stepped wedge clusterrandomized design is similar to a cross over design in that each cluster receives both the treatment and control over time. Each chapter generally has an introduction to the topic, technical details including power and sample size calculation details, explanations for the procedure. While the literature is rich for standard parallel or clustered randomised clinical trials crts, it is much less so for swts. The analysis software will include methods to identify outlying data elements cluster, period, or cluster period with large influence on study results, to establish robustness as well as statistical options for finitesample bias corrections to account for the small numbers of clusters common to stepped wedge trials. Tests for two means in a stepped wedge clusterrandomized design incomplete design custom. This method involves specification of the number of steps t, number of clusters randomized per step g, the number of observations per cluster per period m, and other conventional parameters, such as the. Although swts are increasingly used, unlike cluster randomised controlled trials crt, no standards exist for reporting or for analysis. Pdf feasibility of a stepped wedge cluster rct and. Stepped wedge designs incorporate data collection at each point where a new group step receives the intervention.
A main advantage of the stepped wedge design was that the intervention rolls out to all participants, motivating patients and doctors, and a large number of patients who were included in this study. Once the intervention is initiated at a site, all participants within that site remain exposed to the intervention for the remainder of the study. In cluster randomized trials, the unit of randomization is the group rather than the individual. Dec, 2018 a stepped wedge cluster randomised trial swcrt is a multicentred study which allows an intervention to be rolled out at sites in a random order. In a traditional rct, a part of the participants in the experiment are simultaneously and randomly assigned to a group that receives the treatment. However, the possibility of transition periods with no observations at all as in. Data will be classified into prenetworkz control, transition and postintervention intervention categories see figure 1. Blandaltman method for assessing agreement in method comparison studies. First, we want to allow for the possibility that betweenperiod sitelevel correlation will decrease or decay over time. Sample size calculation for steppedwedge clusterrandomized. This procedure computes power and sample size for tests for the difference between two proportions in cross. Tests for two proportions in a steppedwedge cluster. Recently, i was helping an investigator plan a stepped wedge cluster randomized trial to study the effects of modifying a physician support system on patientlevel diabetes management. This is a multidisciplinary care program to identify and treat depression, and to.
Tests for two means in a stepped wedge clusterrandomized design complete design. Current issues in the design and analysis of stepped wedge trials. Contemporary clinical trials 28, 182191 for binary outcomes underestimates the power in some regions of the parameter spaces, and overestimates it in others. Sample size calculation for a stepped wedge trial trials. The optimal design of stepped wedge trials with equal. Evaluation of the effect of multidisciplinary simulation.
In particular, to assess the intervention effect, we will use a poisson model with random site and provider within site effects. There is a gap in current literature of the stepped wedge design for cluster randomization trials for dealing with this specific scenario. The power of steppedwedge designs our data generation. Hence, a power calculation specific to stepped wedge designs is required. Stepped wedge designs can be analyzed using a variety of techniques for longitudinal outcomes that allow for clustering and covariate effects. Stepped wedge design in the stepped wedge design, all clusters in a trial will receive the intervention at some point, but the start of the intervention will be staggered.
When calculating sample size or power for stepped wedge or other types of longitudinal cluster randomized trials, it is critical that the planned sampling structure be accurately specified. However, it delivers less power than a stepped wedge design with four or more steps whatever the value of the intracluster correlation. The analysis of effect of pf on the abcs outcome measures in the context of a stepped wedge design will be based on a generalized linear mixed model glmm. Effective sample size is number of clusters, not number of. List of sample size procedures sample size software pass. Wedge provides powerful process analytics to improve your industrial plant efficiency. Feasibility of a stepped wedge cluster rct and concurrent. Sample size calculation for a stepped wedge trial trials full text. Stepped wedge using manual approach for proportions 51. Our method covers both standard stepped wedge designs i. Randomization determines when the intervention starts. Stepped wedge designs could reduce the required sample. In this study, we classi ed stepped wedge trial designs according to.
Introduction swsamp is an r package designed to allow a wide range of simulationbased sample size calculations, specifically but not exclusively. Stepped wedge randomised trial designs involve sequential rollout of an intervention to participants individuals or clusters over a number of time periods. Stepped wedge designs could reduce the required sample size in. Sep 25, 2014 i am looking for an advice on sample size and power calculation for an intervention study. Conduct statistical power analysis and calculate probabilities as well as some more test cases with the help of this. Use the links below to load individual chapters from the pass statistical software training documentation in pdf format. Contains functions for closedform sample size calculation based on a set of specific models and simulationbased procedures that can extend the basic framework. Planning and analysis of trials using a stepped wedge design. However, the stepped wedge design additionally has a withincluster element that is, all clusters provide intervention and control data, which provides power advantages to a parallel cluster rct in a similar way to the comparison of paired with unpaired t tests. Sample size in the pre and post period is the same n pre or post. Jul 09, 2017 recently, i was helping an investigator plan a stepped wedge cluster randomized trial to study the effects of modifying a physician support system on patientlevel diabetes management. Standardised guidance for reporting stepped wedge trials is currently absent, and a range of potential analytic approaches have been described. Most trials employed either a gee or mixed model approach to analysis n 77 but only 22 trials 22 % estimated sample size in a way which accounted for the stepped wedge design that was subsequently used.
724 1266 919 57 1057 1241 662 39 556 323 982 26 1496 890 1366 1302 57 1286 47 906 1425 51 760 1 358 1393 655 612 245 616 758 234