摘要
目的为多元线性回归分析数据可视化提供方法参考。方法数据加载入R Studio软件后首先构建全域数据之间关系,进一步拟合自变量与因变量的线性关系,在确认观察值的独立性、因变量的正态性、变量间线性关系满足条件的基础上进行初步建模,然后进行参数估计、多重共线性识别处理、显著性检验和残差分析来校正数据保证模型构建,最后运用模型进行预测。结果R Studio软件在实现多元线性回归分析较传统R语言软件具有更好的可视化功能和更简便的操作。结论R Studio软件在实现多元线性回归分析数据可视化中具有较好的应用价值。
Objective To provide method references for data visualization of multiple linear regression analysis.Methods After importing data to R Studio,this paper conducted general descriptive statistics analysis,then constructed a linear model between independent variables and the target.After checking independence of observations,the normality of the target,and the linearity between variables,this paper estimated coefficients of independent variables,dealt with multicollinearity,tested significance of estimates and performed residual analysis to guarantee that the regression met its assumptions,and eventually used the fitted model for prediction.Results The multiple linear regression analysis implemented by R Studio software had better visualization functions and easier operation than traditional R language software.Conclusions R Studio software has good application value in realizing multiple linear regression analysis data visualization.
作者
李多多
俞兴
韩晟
朱贺
苑艺
沈捷
林景峰
黎霞
甘叶娜
刘建平
LI Duoduo;YU Xing;HAN Sheng;ZHU He;YUAN Yi;SHEN Jie;LIN Jingfeng;LI Xia;GAN Yena;LIU Jianping(Dongzhimen Hospital,Beijing University of Chinese Medicine,Beijing 100700,P.R.China;School of Pharmaceutical Science,Peking University,Beijing 100191,P.R.China;International Research Center for Medicinal Administration,Peking University,Beijing 100191,P.R.China;iHealth Labs Inc,Shanghai 200235,P.R.China;Dongfang Hospital,Beijing University of Chinese Medicine,Beijing 100078,P.R.China;Centre for Evidence-Based Chinese Medicine,Beijing University of Chinese Medicine,Beijing 100029,P.R.China)
出处
《中国循证医学杂志》
CSCD
北大核心
2021年第4期482-490,共9页
Chinese Journal of Evidence-based Medicine
基金
国家自然科学基金项目(编号:81830115)。
