Javitt J C
Dana Center for Preventive Ophthalmology, Wilmer Ophthalmological Institute, Johns Hopkins University, Baltimore, Md.
Arch Ophthalmol. 1989 Jul;107(7):1034-40. doi: 10.1001/archopht.1989.01070020096040.
When a published clinical report concludes that there is no difference between two or more groups of patients, the reader must discern between two alternative possibilities. Either there is truly no difference in outcome between the groups or the study failed to detect an actual difference. The application of sample size and power calculations to outcome variables in a clinical study can provide essential insight into resolving this ambiguity. While one can never prove that there is no difference between groups of patients, these techniques can estimate the likelihood that a particular study will detect or fail to detect a difference of specified size.
当一份已发表的临床报告得出两组或多组患者之间没有差异的结论时，读者必须辨别两种可能性。要么各组之间在结果上确实没有差异，要么该研究未能检测到实际存在的差异。在临床研究中对样本量和检验效能计算应用于结局变量，可以为解决这种模糊性提供重要的见解。虽然永远无法证明患者组之间没有差异，但这些技术可以估计特定研究检测到或未能检测到指定大小差异的可能性。
