Blomqvist N
J Clin Periodontol. 1985 Nov;12(10):873-6. doi: 10.1111/j.1600-051x.1985.tb01365.x.
It is stated that in trials where experimental units on different levels (sites, patients, etc.) are employed, the highest level unit should be used as computational unit when computing standard errors and in statistical inference. Using a lower level unit will underestimate the standard error and the level of significance (P-value). A numerical illustration is presented.
据说，在使用不同层次（地点、患者等）的实验单位的试验中，在计算标准误差和进行统计推断时，应将最高层次的单位用作计算单位。使用较低层次的单位会低估标准误差和显著性水平（P值）。本文给出了一个数值示例。
