如何正确运用t检验——两几何均值比较一般差异性t检验及SAS实现  

How to use t test correctly——comparison of two geometric means with general difference t test and SAS implementation

作　　者：于泽洋 刘媛媛[1] 李长平[1,2] 胡良平 Yu Zeyang;Liu Yuanyuan;Li Changping;Hu Liangping(Department of Health Statistics,School of Public Health,Tianjin Medical University,Tianjin 300070,China;Specialty Committee of Clinical Scientific Research Statistics of World Federation of Chinese Medicine Societies,Beijing 100029,China;Graduate School,Academy of Military Sciences PLA China,Beijing 100850,China)

机构地区：[1]天津医科大学公共卫生学院,天津300070 [2]世界中医药学会联合会临床科研统计学专业委员会,北京100029 [3]军事科学院研究生院,北京100850

出　　处：《四川精神卫生》2020年第3期222-225,共4页Sichuan Mental Health

基　　金：国家自然科学基金项目(项目名称:贝叶斯生存分析方法在肝细胞癌肝移植患者预后预测中的应用研究,项目编号:81803333)。

摘　　要：本文目的是介绍几何均数以及两组近似对数正态分布数据几何均数的一般差异性t检验及SAS实现。首先对几何均数的概念、适用条件和计算公式进行介绍;并且将几何均数与统计学中常用的算术均数的特点进行比较;其次,呈现两组药物浓度数据,该数据近似服从对数正态分布,符合几何均数的适用条件,使用SAS的TTEST过程对两组几何均数的一般差异性进行t检验,并对相关结果进行解释和比较;最后,讨论几何均数使用时的注意事项。The purpose of this article was to introduce the geometric mean,as well as the SAS implementation of general difference t test for logarithmic normal distribution data.Firstly,the concept of geometric mean,applicable conditions and calculation formulas were introduced.And the characteristics of geometric means were compared with those of arithmetic means commonly used in statistics.Secondly,two groups of concentration data were presented,which were logarithmic normal distribution approximately and met the applicable conditions of the geometric mean.The TTEST procedure of SAS was used to perform a t test on the general difference of the geometric mean.The relevant results were explained and compared.Finally,the precautions when using geometric mean were discussed.

关 键 词：几何均数 对数正态分布 变量变换 T检验 SAS软件 

分 类 号：R195.1[医药卫生—卫生统计学]