方法对比

	阻塞 A/B 测试	分块随机对照试验
领域	实验设计	实验设计
方法族	Process / pipeline	Process / pipeline
起源年份	1926 (blocking principle); 2000s–2010s (online A/B testing application)	1920s (Fisher's blocking principle); applied to RCTs from the 1940s onward
提出者	R. A. Fisher (blocking principle); adapted to online A/B testing by industry practitioners	R. A. Fisher (blocking principle); systematic RCT application by Bradford Hill and later Pocock, Friedman et al.
类型	Randomized controlled experiment with variance reduction	Experimental design
开创性文献	Fisher, R. A. (1926). The arrangement of field experiments. Journal of the Ministry of Agriculture of Great Britain, 33, 503–513.	Friedman, L. M., Furberg, C. D., DeMets, D. L., Reboussin, D. M., & Granger, C. B. (2010). Fundamentals of Clinical Trials (4th ed.). Springer. ISBN: 978-1441915856
别名	block-randomized A/B test, stratified A/B test, blocked split test, block-design A/B experiment	blocked RCT, block-randomized trial, stratified block randomization trial, permuted block randomization
相关	4	5
摘要	A blocked A/B test is an experimental design that partitions units (users, subjects, or clusters) into homogeneous blocks before randomly assigning them to treatment A or treatment B within each block. Blocking reduces within-experiment noise by ensuring that known sources of variation — such as device type, geography, or user tenure — are balanced across conditions, yielding more precise estimates of the treatment effect than a simple unblocked A/B test.	A blocked randomized controlled trial (blocked RCT) uses permuted-block randomization to ensure that treatment groups remain balanced in size — and optionally in key characteristics — throughout recruitment. Within each block of fixed or randomly varied size, all treatment allocations are present in equal numbers, so imbalance cannot accumulate even if the trial is stopped early. This makes blocked RCTs the standard randomization approach in clinical and behavioral intervention research.