| 黄丽红,魏永越,陈峰.如何控制观察性疗效比较研究中的混杂因素：（一）已测量混杂因素的统计学分析方法[J].Chinese journal of Epidemiology,2019,40(10):1304-1309 |
| 如何控制观察性疗效比较研究中的混杂因素：（一）已测量混杂因素的统计学分析方法 |
| Confounder adjustment in observational comparative effectiveness researches: (1) statistical adjustment approaches for measured confounder |
| Received:March 18, 2019 |
| DOI：10.3760/cma.j.issn.0254-6450.2019.10.024 |
| KeyWord: 观察性疗效比较研究 现实世界研究 已测量混杂 控制 统计方法 |
| English Key Word: Observational comparative effectiveness research Real world study Measured confounder Adjustment Statistical method |
| FundProject:观察性疗效比较研究；现实世界研究；已测量混杂；控制；统计方法基金项目：国家自然科学青年基金（81903407） |
| Author Name | Affiliation | E-mail | | Huang Lihong | Department of Biostatistics, Zhongshan Hospital, Fudan University, Shanghai, 200032, China | huang.lihong@zs-hospital.sh.cn | | Wei Yongyue | Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, 211166, China | | | Chen Feng | Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, 211166, China | |
|
| Hits: 5599 |
| Download times: 2252 |
| Abstract: |
| 观察性疗效比较研究作为随机对照研究的补充，其应用价值越来越受到关注，混杂偏倚是其重要偏倚来源。本文介绍观察性疗效比较研究中已测量的混杂因素控制的统计分析方法。对于已测量的混杂因素，可采用传统的分层分析、配对分析、协方差分析或多因素分析，也可采用倾向性评分、疾病风险评分等方法进行混杂因素匹配、分层和调整。良好的设计需从源头控制各种混杂，事后统计分析则应在理解各类方法的应用前提下，严格把握适用条件。 |
| English Abstract: |
| Observational comparative effectiveness studies have been widely conducted to provide evidence on additional effectiveness and to support randomized controlled findings in research. Although this type of study becomes more important over time, challenges related to the common biases which stemmed from confounders, are difficult to control. This manuscript summarizes some statistical methods used on adjusting measured confounders that often noticed in research, regarding the observational comparative effectiveness. Useful traditional methods would include stratified analysis, paired analysis, covariate model and multivariable model, etc.. Unconventional adjustment approaches such as propensity score and disease risk score methods may also be used in studies, for matching, stratification and adjustment. A good study design should be able to control confounders. The limitations of all the post hoc statistical adjustment methods should also be fully understood before being appropriately applied in practical events. |
|
View Fulltext
Html FullText
View/Add Comment Download reader |
| Close |
|
|
|