Key Design Considerations Using a Cohort Stepped-Wedge Cluster Randomised Trial in Evaluating Community-Based Interventions: Lessons Learnt from an Australian Domiciliary Aged Care Intervention Evaluation

Mohammadreza Mohebbi; Masoumeh Sanagou; Goetz Ottmann

doi:10.6000/1929-6029.2017.06.03.4

Authors

Mohammadreza Mohebbi Biostatistics Unit, Deakin University, Geelong, Australia
Masoumeh Sanagou Australian Radiation Protection and Nuclear Safety Agency, Lower Plenty Road, Yallambie, Victoria 3085, Australia
Goetz Ottmann Australian College of Applied Psychology, Sydney, Australia

DOI:

https://doi.org/10.6000/1929-6029.2017.06.03.4

Keywords:

Clinical trials, Stepped wedge design, missing data, sample size, Cluster randomized trial

Abstract

The ‘stepped-wedge cluster randomised trial’ (SW-CRT) harbours promise when for ethical or practical reasons the recruitment of a control group is not possible or when a staggered implementation of an intervention is required. Yet SW-CRT designs can create considerable challenges in terms of methodological integration, implementation, and analysis. While cross-sectional methods in participants recruitment of the SW-CRT have been discussed in the literature the cohort method is a novel feature that has not been considered yet. This paper provides a succinct overview of the methodological, analytical, and practical aspects of cohort SW-CRTs. We discuss five issues that are of special relevance to SW-CRTs. First, issues relating to the design, secondly size of clusters and sample size; thirdly, dealing with missing data in the fourth place analysis; and finally, the advantages and disadvantages of SW-CRTs are considered. An Australian study employing a cohort SW-CRT to evaluate a domiciliary aged care intervention is used as case study. The paper concludes that the main advantage of the cohort SW-CRT is that the intervention rolls out to all participants. There are concerns about missing a whole cluster, and difficulty of completing clusters in a given time frame due to involvement frail older people. Cohort SW-CRT designs can be successfully used within public health and health promotion context. However, careful planning is required to accommodate methodological, analytical, and practical challenges.

References

Hemming K, Haines TP, Chilton PJ, Girling AJ, Lilford RJ. The stepped wedge cluster randomised trial: rationale, design, analysis, and reporting. BMJ 2015; 350. https://doi.org/10.1136/bmj.h391 DOI: https://doi.org/10.1136/bmj.h391

Hemming K, Lilford R, Girling AJ. Stepped-wedge cluster randomised controlled trials: a generic framework including parallel and multiple-level designs. Stat Med 2015; 34(2): 181-96. https://doi.org/10.1002/sim.6325 DOI: https://doi.org/10.1002/sim.6325

Hussey MA, Hughes JP. Design and analysis of stepped wedge cluster randomized trials. Contemp Clin Trials 2007; 28(2): 182-91. https://doi.org/10.1016/j.cct.2006.05.007 DOI: https://doi.org/10.1016/j.cct.2006.05.007

Woertman W, de Hoop E, Moerbeek M, Zuidema SU, Gerritsen DL, Teerenstra S. Stepped wedge designs could reduce the required sample size in cluster randomized trials. J Clin Epidemiol 2013; 66(7): 752-8. https://doi.org/10.1016/j.jclinepi.2013.01.009 DOI: https://doi.org/10.1016/j.jclinepi.2013.01.009

Brown CA, Lilford RJ. The stepped wedge trial design: a systematic review. BMC Med Res Methodol 2006; 6: 54. https://doi.org/10.1186/1471-2288-6-54 DOI: https://doi.org/10.1186/1471-2288-6-54

Mdege ND, Man MS, Taylor Nee Brown CA, Torgerson DJ. Systematic review of stepped wedge cluster randomized trials shows that design is particularly used to evaluate interventions during routine implementation. J Clin Epidemiol 2011; 64(9): 936-48. https://doi.org/10.1016/j.jclinepi.2010.12.003 DOI: https://doi.org/10.1016/j.jclinepi.2010.12.003

Feldman HA, McKinlay SM. Cohort versus cross-sectional design in large field trials: precision, sample size, and a unifying model. Stat Med 1994; 13(1): 61-78. https://doi.org/10.1002/sim.4780130108 DOI: https://doi.org/10.1002/sim.4780130108

Zhan Z, van den Heuvel ER, Doornbos PM, Burger H, Verberne CJ, Wiggers T, de Bock GH. Strengths and weaknesses of a stepped wedge cluster randomized design: its application in a colorectal cancer follow-up study. J Clin Epidemiol 2014; 67(4): 454-61. https://doi.org/10.1016/j.jclinepi.2013.10.018 DOI: https://doi.org/10.1016/j.jclinepi.2013.10.018

Ottmann G, Millicer A, Bates A. CHOICES in Community Aged Care: Final Report, Uniting Care Life Assist/Deakin University Research Partnership, QPS, Glen Waverley 2015.

de Hoop E, Woertman W, Teerenstra S. The stepped wedge cluster randomized trial always requires fewer clusters but not always fewer measurements, that is, participants than a parallel cluster randomized trial in a cross-sectional design. In reply. J Clin Epidemiol 2013; 66(12): 1428. https://doi.org/10.1016/j.jclinepi.2013.07.008 DOI: https://doi.org/10.1016/j.jclinepi.2013.07.008

Hemming K, Girling AJ. A menu-driven facility for power and detectable difference calculations in stepped-wedge randomized trials. The Stata Journal 2014; 14(2): 363-380. DOI: https://doi.org/10.1177/1536867X1401400208

Harville DA. Maximum likelihood approaches to variance component estimation and to related problems. Journal of the American Statistical Association 1977; 72(3): 320-338. https://doi.org/10.1080/01621459.1977.10480998 DOI: https://doi.org/10.1080/01621459.1977.10480998

Liang KY, Zeger SL. Longitudinal data analysis using generalized linear models. Biometrika 1986; 73: 13-22. https://doi.org/10.1093/biomet/73.1.13 DOI: https://doi.org/10.1093/biomet/73.1.13

Murray DM, Varnell SP, Blitstein JL. Design and analysis of group-randomized trials: a review of recent methodological developments. Am J Public Health 2004; 94(3): 423-32. https://doi.org/10.2105/AJPH.94.3.423 DOI: https://doi.org/10.2105/AJPH.94.3.423

Rice N, Leyland A. Multilevel models: applications to health data. J Health Serv Res Policy 1996; 1(3): 154-64. DOI: https://doi.org/10.1177/135581969600100307

Merlo J, Lynch JW, Yang M, Lindstrom M, Ostergren PO, Rasmusen NK, Rastam L. Effect of neighborhood social participation on individual use of hormone replacement therapy and antihypertensive medication: a multilevel analysis. Am J Epidemiol 2003; 157(9): 774-83. https://doi.org/10.1093/aje/kwg053 DOI: https://doi.org/10.1093/aje/kwg053

Merlo J. Multilevel analytical approaches in social epidemiology: measures of health variation compared with traditional measures of association. J Epidemiol Community Health 2003; 57(8): 550-2. https://doi.org/10.1136/jech.57.8.550 DOI: https://doi.org/10.1136/jech.57.8.550

Clarke P. When can group level clustering be ignored? Multilevel models versus single-level models with sparse data. J Epidemiol Community Health 2008; 62(8): 752-8. https://doi.org/10.1136/jech.2007.060798 DOI: https://doi.org/10.1136/jech.2007.060798

Lachin JM. Statistical considerations in the intent-to-treat principle. Control Clin Trials 2000; 21(3): 167-89. https://doi.org/10.1016/S0197-2456(00)00046-5 DOI: https://doi.org/10.1016/S0197-2456(00)00046-5

Abraha I, Cherubini A, Cozzolino F, De Florio R, Luchetta ML, Rimland JM, Folletti I, Marchesi M, Germani A, Orso M, Eusebi P, Montedori A. Deviation from intention to treat analysis in randomised trials and treatment effect estimates: meta-epidemiological study. BMJ 2015; 350. https://doi.org/10.1136/bmj.h2445 DOI: https://doi.org/10.1136/bmj.h2445

Bell ML, Kenward MG, Fairclough DL, Horton NJ. Differential dropout and bias in randomised controlled trials: when it matters and when it may not. BMJ 2013; 346: e8668. https://doi.org/10.1136/bmj.e8668 DOI: https://doi.org/10.1136/bmj.e8668

Ware JE Jr, Kosinski M, Keller SD. A 12-Item Short-Form Health Survey: construction of scales and preliminary tests of reliability and validity. Medical Care 1996; 34(3): 220-233. https://doi.org/10.1097/00005650-199603000-00003 DOI: https://doi.org/10.1097/00005650-199603000-00003

Bell ML, Fairclough DL. Practical and statistical issues in missing data for longitudinal patient-reported outcomes. Stat Methods Med Res 2014; 23(5): 440-59. https://doi.org/10.1177/0962280213476378 DOI: https://doi.org/10.1177/0962280213476378

Little R, Rubin D. Statistical Analysis With Missing Data, Wiley, Hoboken, NJ 2002. https://doi.org/10.1002/9781119013563 DOI: https://doi.org/10.1002/9781119013563

Taljaard M, Donner A, Klar N. Imputation strategies for missing continuous outcomes in cluster randomized trials. Biometrical Journal 2008; 50(3): 329-45. https://doi.org/10.1002/bimj.200710423 DOI: https://doi.org/10.1002/bimj.200710423

Ma J, Akhtar-Danesh N, Dolovich L, Thabane L. Imputation strategies for missing binary outcomes in cluster randomized trials. BMC Med Res Methodol 2011; 11: 18. https://doi.org/10.1186/1471-2288-11-18 DOI: https://doi.org/10.1186/1471-2288-11-18

DeSouza CM, Legedza AT, Sankoh AJ. An overview of practical approaches for handling missing data in clinical trials. J Biopharm Stat 2009; 19(6): 1055-73. https://doi.org/10.1080/10543400903242795 DOI: https://doi.org/10.1080/10543400903242795

Sterne JA, White IR, Carlin JB, Spratt M, Royston P, Kenward MG, Wood AM, Carpenter JR. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ 2009; 338. https://doi.org/10.1136/bmj.b2393 DOI: https://doi.org/10.1136/bmj.b2393

O'Neill RT, Temple R. The prevention and treatment of missing data in clinical trials: an FDA perspective on the importance of dealing with it. Clin Pharmacol Ther 2012; 91(3): 550-4. https://doi.org/10.1038/clpt.2011.340 DOI: https://doi.org/10.1038/clpt.2011.340

Ottmann G, Mohebbi M. Self-directed community services for older Australians: a stepped capacity-building approach, Health Soc Care Community 2014; 22(6): 598-611. https://doi.org/10.1111/hsc.12111 DOI: https://doi.org/10.1111/hsc.12111

Teddlie C, Abbas T. Overview of contemporary issues in mixed methods research. Sage handbook of mixed methods in social and behavioral research 2010; pp. 1-44. https://doi.org/10.4135/9781506335193.n1 DOI: https://doi.org/10.4135/9781506335193.n1

Kotz D, Spigt M, Arts IC, Crutzen R, Viechtbauer W. Use of the stepped wedge design cannot be recommended: a critical appraisal and comparison with the classic cluster randomized controlled trial design. J Clin Epidemiol 2012; 65(12): 1249-52. https://doi.org/10.1016/j.jclinepi.2012.06.004 DOI: https://doi.org/10.1016/j.jclinepi.2012.06.004

Mdege ND, Man MS, Taylor nee Brown CA, Torgerson DJ. There are some circumstances where the stepped-wedge cluster randomized trial is preferable to the alternative: no randomized trial at all. Response to the commentary by Kotz and colleagues. J Clin Epidemiol 2012; 65(12): 1253-4. https://doi.org/10.1016/j.jclinepi.2012.06.003 DOI: https://doi.org/10.1016/j.jclinepi.2012.06.003

Campbell MK, Piaggio G, Elbourne DR, Altman DG. Consort 2010 statement: extension to cluster randomised trials. BMJ 2012; 345: e5661. https://doi.org/10.1136/bmj.e5661 DOI: https://doi.org/10.1136/bmj.e5661

Zwarenstein M, Treweek S, Gagnier JJ, Altman DG, Tunis S, Haynes B, Oxman AD, Moher D. Improving the reporting of pragmatic trials: an extension of the CONSORT statement BMJ 2008; 337: a2390. https://doi.org/10.1136/bmj.a2390 DOI: https://doi.org/10.1136/bmj.a2390

Piantadosi S, Byar DP, Green SB. The ecological fallacy. Am J Epidemiol 1988; 127(5): 893-904. https://doi.org/10.1093/oxfordjournals.aje.a114892 DOI: https://doi.org/10.1093/oxfordjournals.aje.a114892

Finney JW, Humphreys K, Kivlahan DR, Harris AH. Why health care process performance measures can have different relationships to outcomes for patients and hospitals: understanding the ecological fallacy. Am J Public Health 2011; 101(9): 1635-42. https://doi.org/10.2105/AJPH.2011.300153 DOI: https://doi.org/10.2105/AJPH.2011.300153

Rasbash J, Goldstein H. Efficient analysis of mixed hierarchical and cross-classified random structures using a multilevel model. Journal of Educational and Behavioral Statistics 1994; 19(4): 337-350. https://doi.org/10.3102/10769986019004337 DOI: https://doi.org/10.3102/10769986019004337

Goldstein H, McDonald RP. A general model for the analysis of multilevel data. Psychometrika 1988; 53(4): 455-467. https://doi.org/10.1007/BF02294400 DOI: https://doi.org/10.1007/BF02294400

Snijders TAB. Power and Sample Size in Multilevel Linear Models, Encyclopedia of Statistics in Behavioral Science, John Wiley & Sons, Ltd. 2005. DOI: https://doi.org/10.1002/0470013192.bsa492

Maas CJ, Hox JJ. Sufficient sample sizes for multilevel modeling. Methodology 2005; 1(3): 86-92. https://doi.org/10.1027/1614-2241.1.3.86 DOI: https://doi.org/10.1027/1614-2241.1.3.86