临床纵向数据缺失的多重填补及其敏感性分析

doi:10.12092/j.issn.1009-2501.2021.09.009

中国临床药理学与治疗学 ›› 2021, Vol. 26 ›› Issue (9): 1037-1041.doi: 10.12092/j.issn.1009-2501.2021.09.009

临床纵向数据缺失的多重填补及其敏感性分析

焦志刚¹，凡如¹，许碧云²，陈思臻¹，臧一腾¹，王诗远¹，陈炳为¹

¹东南大学公共卫生学院流行病与卫生统计系，南京 210009，江苏；²南京大学医学院附属鼓楼医院医学统计分析中心，南京 210008，江苏

收稿日期:2021-05-10 修回日期:2021-07-27 出版日期:2021-09-26 发布日期:2021-09-30
通讯作者: 陈炳为，男，博士，副教授，硕士生导师，研究方向：生物统计及其应用。 Tel: 18105160373 E-mail: drchenbw@126.com
作者简介:焦志刚，男，硕士研究生，研究方向：生物统计及其应用。 Tel: 15151822987 E-mail: 220193545@seu.edu.cn
基金资助:
江苏省自然科学基金青年项目（BK20190357）

Multiple imputation of missing data in clinical longitudinal studies and its sensitivity analyses

JIAO Zhigang¹, FAN Ru ¹, XU Biyun², CHEN Sizhen ¹, ZANG Yiteng ¹, WANG shiyuan¹, CHEN Bingwei ¹

¹ Department of Epidemiology and Health Statistics, School of Public Health, Southeast University, Nanjing 210009, Jiangsu, China; ²Medical Statistics Analysis Center, Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, Jiangsu, China

Received:2021-05-10 Revised:2021-07-27 Online:2021-09-26 Published:2021-09-30

摘要/Abstract

摘要： 目的：以芪蛭通络胶囊治疗缺血性脑卒中临床试验为例来指导临床纵向数据缺失的多重填补及其敏感性分析，并强调敏感性分析的重要性。方法：应用SAS中的PROC MI过程实现临床纵向数据缺失的多重填补及其敏感性分析。结果：实例分析中，多重填补后，芪蛭通络组的下肢运动评分改善值优于安慰剂组（P值均小于0.01），而两种非随机缺失机制假定下的敏感性分析结果与随机缺失下的结果一致。结论：多重填补结合使用敏感性分析可以确保多重填补结果的稳健性，建议临床研究者对数据填补后还要进行敏感性分析。

关键词: 多重填补, 纵向数据, 敏感性分析

Abstract: AIM: To guide the multiple imputation of missing data in clinical longitudinal studies and its sensitivity analyses, and highlight the importance of sensitivity analyses by taking the clinical trial of Qizhitongluo Capsule in treating ischemic stroke as an example. METHODS: To implement PROC MI process in SAS to perform multiple imputation and its sensitivity analysis. RESULTS: In the example, after multiple imputation, improvements in lower limb motor scores of the Qizhitongluo group were greater than those of the placebo group (all P<0.01), and the results of two sensitivity analyses under "missing not at random" were consistent with those under "missing at random".CONCLUSION: Multiple imputations combined with sensitivity analyses can ensure a robust result. It is recommended that clinical researchers perform sensitivity analyses after filling missing data.

Key words: multiple imputation, longitudinal data, sensitivity analysis

中图分类号:

Q348
R195.4

焦志刚, 凡如, 许碧云, 陈思臻, 臧一腾, 王诗远, 陈炳为. 临床纵向数据缺失的多重填补及其敏感性分析[J]. 中国临床药理学与治疗学, 2021, 26(9): 1037-1041.

JIAO Zhigang, FAN Ru, XU Biyun, CHEN Sizhen, ZANG Yiteng, WANG shiyuan, CHEN Bingwei . Multiple imputation of missing data in clinical longitudinal studies and its sensitivity analyses[J]. Chinese Journal of Clinical Pharmacology and Therapeutics, 2021, 26(9): 1037-1041.

临床纵向数据缺失的多重填补及其敏感性分析

Multiple imputation of missing data in clinical longitudinal studies and its sensitivity analyses

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价