The split-plot design was useful for evaluating complex, multi-level interventions but there is need for improvement in its design and report

Publication date: Available online 4 November 2017
Source:Journal of Clinical Epidemiology
Author(s): Beatriz Goulão, Graeme MacLennan, Craig Ramsay
ObjectiveTo describe the sample size calculation, analysis and reporting of split-plot randomised controlled trials (RCT) in healthcare (trials that use two units of randomisation: one at a cluster-level and one at a level lower than the cluster).Study Design and SettingWe carried out a comprehensive search in the EMBASE database from 1946 to 2016. Healthcare trials with a split-plot design in human subjects were included. Three authors screened and assessed the studies and data were extracted on methodology and reporting standards based upon CONSORT.Results18 split-plot studies were included, with authors using nine different designations to describe them. Units of randomisation were unclear in nine abstracts. Explicit rationale for choosing the design was not givenTen studies presented a sample size calculation accounting for clustering; the analyses were coherent with that. Flow of participant diagrams were presented but incomplete in 14 articles.ConclusionSplit-plot designs can be useful complex designs, but challenging to report. Researchers need to clearly describe the rationale, sample size calculation and participant flow. We provide a suggested CONSORT style participant flow diagram to aid reporting. There is need for more research regarding sample size calculation for split-plots.



from ! ORL Sfakianakis via paythelady.61 on Inoreader http://ift.tt/2zO028u
via IFTTT