方法对比

	簇随机适应性试验	整群随机对照试验
领域	实验设计	实验设计
方法族	Process / pipeline	Process / pipeline
起源年份	2000s–2010s	1978–1980s
提出者	Synthesised from cluster randomization methodology (Donner, 1978; Donner & Klar, 2000) and adaptive design frameworks (Bauer & Kohne, 1994; Pallmann et al., 2018)	Cornfield (1978); systematised by Donner and colleagues (1980s)
类型	Experimental design	Experimental design
开创性文献	Hayes, R. J., & Moulton, L. H. (2017). Cluster Randomised Trials (2nd ed.). CRC Press / Chapman & Hall. ISBN: 978-1498728225	Donner, A., & Klar, N. (2000). Design and Analysis of Cluster Randomization Trials in Health Research. Arnold. ISBN: 978-0340652978
别名	adaptive cluster RCT, adaptive group-randomized trial, cluster adaptive design, adaptive cluster trial	cluster RCT, group-randomized trial, community randomized trial, cluster-randomized experiment
相关	5	4
摘要	A cluster randomized adaptive experiment combines two methodological principles: (1) intact groups such as schools, clinics, or villages are randomly assigned to treatment conditions rather than individuals, and (2) pre-specified rules allow the design to be modified during the trial based on accumulating cluster-level data. Adaptations may include dropping underperforming arms, reallocating clusters, or adjusting sample size, while maintaining statistical validity and controlling Type I error.	A cluster randomized controlled trial (cluster RCT) is an experimental design in which intact social or organisational groups — such as schools, clinics, villages, or workplaces — are randomly assigned to treatment conditions rather than individual participants. Outcomes are still measured at the individual level, but the unit of randomization is the cluster. This design is essential when an intervention is delivered to whole groups, when there is a risk of contamination between participants in the same setting, or when individual randomization is logistically or ethically impractical.