| 闫宇翔,王洪源,王仁安.多临床终点的等效性检验方法探讨[J].Chinese journal of Epidemiology,2003,24(10):935-938 |
| 多临床终点的等效性检验方法探讨 |
| Statistical test on multivariate in therapautical equivalence analysis |
| Received:December 06, 2002 |
| DOI： |
| KeyWord: 临床等效性 多变量等效性检验 相关性 |
| English Key Word: Ther apeutic equivalence Multivariate test of equivalence Correlation |
| FundProject: |
|
| Hits: 3180 |
| Download times: 1045 |
| Abstract: |
| 目的探讨多临床终点的等效性检验方法。方法应用改进的HotellingT2检验对两组均数向量进行等效性检验,通过扣除变量间相关性的方法获得各变量是否等效的具体信息;并结合实例进行分析,以±2%为等效界值的上下界,对“A、B两药治疗绝经后骨质疏松症”的四个疗效指标分别进行单变量和多变量等效性检验,比较其结果。结果当HotellingT2检验的统计量对应的P>α时,可认为所有变量不等效;若P≤α时,应进行不等效变量的筛选,经筛选无不等效变量可认为其等效,若经筛选有不等效变量,则认为该变量不等效,该方法克服了重复单变量等效性检验的缺点。结论应用改进的HotellingT2检验并结合不等效变量的筛选方法,可以对多个临床终点同时进行等效性检验,该方法合理且可操作 |
| English Abstract: |
| Objective To explore the way for test ing of multivariate in therapautical equiv alence.Methods By impro ved Hotelling T 2 test, the mean vector of two groups was tested. The informat ion of each variable could then be obtained by deducting t he t heir cor relations. Clinical Equivalence of Drug A and Drug B for Postmenopausal Bone Looseness was used in this resear ch. The primary measure o f efficacy was r eg ar ded as the improvement rate o f four variables with predefined limit of equivalence ( 2%) wit h the r esults of univariate test and multivariate test compared. Results Under P, all the variables were nonequivalent. Under P, it was necessar y to filtrate the variables of unequivalent until the residuals were equivalent. The method of mult ivariate test was a r emedy to the shortage of univ ar iate test. Conclusion With the combinatio n of the filtration of nonequivalent variables and the improved Hotelling T 2 test, the t est of multivariate could be done. T he method is reasonable and practical. |
|
View Fulltext
Html FullText
View/Add Comment Download reader |
| Close |
|
|
|