广义估计方程与混合线性模型在Python中的实现  

Implementation of generalized estimating equations and mixed linear models in Python

作　　者：焦奎壮 马煦晰 马小茜 刘朝屹 张青 马露[1] Kui-Zhuang JIAO;Xu-Xi MA;Xiao-Qian MA;Chao-Yi LIU;Qing ZHANG;Lu MA(School of Public Health,Wuhan University,Wuhan 430071,China)

机构地区：[1]武汉大学公共卫生学院,武汉430071

出　　处：《医学新知》2022年第5期333-338,共6页New Medicine

基　　金：湖北省卫生健康委2021—2022年度科研项目(WJ2021F103)。

摘　　要：目的探索纵向数据分析中广义估计方程和混合线性模型在Python中的实现方法,拓展Python软件在统计分析中的应用。方法通过Python软件构建广义估计方程和混合线性模型,以环境流行病学的研究实例探索大气颗粒物PM_(2.5)对肺功能的影响,并与R软件分析结果进行比较。结果PM_(2.5)是肺功能降低的危险因素,PM_(2.5)每升高1μg/m^(3),研究对象2天后第1秒用力呼气容积减少8 mL。Python软件可用statsmodels库进行广义估计方程和混合线性模型的分析,实现过程程序语言简洁。与R软件相比,程序逻辑具有一定的相似性,参数估计和置信区间的计算结果基本一致,Python结果可信。结论Python软件可灵活构建广义估计方程和混合线性模型,在实际研究中有一定参考价值。Objective Explore the implementation of generalized estimation equations(GEE)and mixed linear models(MLM)in longitudinal data analysis using Python software,and expand its application in statistical analysis.Methods GEE and MLM were constructed by Python software to explore the impact of PM_(2.5) on lung function(forced expiratory volume in1second,FEV1)with an example of environmental epidemiology,and compared with the results of R software.Results With PM_(2.5) increases of 1μg/m^(3),the FEV1 of the subjects decreased by 8 mL after 2 days.Python software can use a statsmodels library to analyze MLM and GEE,and the program language is concise,the program logic has a certain similarity when compared with R,the calculation results of parameter estimation and confidence interval are almost the same,and the Python result is reliable.Conclusion Python software can flexibly construct MLM and GEE,which has a certain reference value in practical research.

关 键 词：PYTHON 广义估计方程 混合线性模型 纵向数据 

分 类 号：TP312.1[自动化与计算机技术—计算机软件与理论] R181.2[自动化与计算机技术—计算机科学与技术]