我们一般翻译为“分组方式”

稳定性指南中均译为括号法，可参考最新的国内指南以及2007年 ICH Q1 指南的中译本

括号法为一种较易理解的试验设计理念，即讨论或检验了两极端的数据（有效），那么（两端）之中的数据也有效。或者用于估计中间数据可能波动的范围。除了在稳定性批次考察之外，在验证时安排装载量，评估溶出度与设计空间时都有应用。例如：

（1） Depyrogenation Study: The component(s) of the loads for the depyrogenation study can be representative of the component(s) in the production loads (such as a worst-case vial or stopper) or can be the component of the drug product. Likewise, the load size(s) can be the same as the production load(s), can bracket the production load size(s), or can be worst-case when compared to the production load size(s). From Example Quality Overall Summary for an for an extended release capsule

（2）Formulation Optimization: A series of studies were performed to investigate the effect of the thickness of the controlled release membrane on dissolution ... three trial formulations having differing CR coating levels (6%, 11%, 16%) were designed such that their dissolution profiles (pH independent) would bracket the RLD dissolution profiles at 6.8. Pilot PK studies in 5 subjects were then performed to determine the coating thickness that would best match the pharmacokinetic profile of the RLD. From Question-based Review (QbR) for Sterility Assurance of Terminally Sterilized Products: Frequently Asked Questions