医学多元统计方法课程模拟案例教学研究  

Research on simulated case teaching in the course of Medical Multiple Statistical Methods

作　　者：王亚茹 王玖[1] 刘海霞[1] 侯静 张莉[1] 李智 孙红卫[1] Wang Yaru;Wang Jiu;Liu Haixia;Hou Jing;Zhang Li;Li Zhi;Sun Hongwei(School of Public Health,Binzhou Medical University,Yantai 264003,China)

机构地区：[1]滨州医学院公共卫生学院,山东烟台264003

出　　处：《中国医院统计》2024年第1期61-66,71,共7页Chinese Journal of Hospital Statistics

基　　金：山东省优质专业学位案例库建设项目(SDYAL2022183)。

摘　　要：目的由于多元统计概念较为复杂,容易导致学生理解上的困难,本文以模拟实验的形式考察数据的各项特征对分析结果的影响,以加强学生对多元统计原理的理解,利于学生正确应用多元统计方法。方法设计6个模拟实验,运用R 4.2.2生成模拟数据并进行统计分析,探寻数据特征对6种统计分析方法的影响。结果由模拟实验的统计分析结果可知,在多重线性回归中自变量间的多重共线性会使得回归方程的回归系数估计不准确。主成分和因子分析中变量间的相关结构影响降维效果。logistic回归中要考虑到自变量对因变量的非线性影响,否则结果会影响到估计结果的准确度。在Cox回归删失比例过大,特别是达到60%后,Cox回归模型结果偏差较大。变量间的相关结构影响典型相关分析结果。类别比例相差较大时,Bayes判别和logistic回归做判别更为合适,由于包含先验概率,贝叶斯判别更加灵活。结论多元统计方法的运用需充分考虑数据特征等适用条件,通过模拟实验法,鼓励学生自主运行模拟实验,直观理解抽象的多元概念,便于多元统计方法的理解和应用。Objective The complexity of the concept of multivariate statistics can easily lead to difficulties in students′understanding.This article uses simulation experiments to examine the impact of various characteristics of data on the analysis results,in order to strengthen students′understanding of the principles of multivariate statistics and facilitate their correct application of multivariate statistical methods.Methods Six simulation experiments were designed,and R 4.2.2 was used to generate simulation data and conduct statistical analysis to explore the impact of data characteristics on the 6 statistical analysis methods.Results According to the statistical analysis results of simulation experiments,the multicollinearity among independent variables in multilinear regression will make the regression coefficient estimation of the regression equation inaccurate.The correlation structure between variables in principal component and factor analysis affects the dimensionality reduction effect.In logistic regression,the nonlinear influence of independent variables on dependent variables should be considered,otherwise the results will affect the accuracy of the estimation results.When the proportion of deletion in Cox regression is too large,especially after reaching 60%,the results of the Cox regression model have a significant deviation.The correlation structure between variables affects the results of canonical correlation analysis.When there is a large difference in the proportion of categories,Bayesian discrimination and logistic regression are more appropriate for discrimination,because Bayesian discrimination with prior probability is more flexible.Conclusion The application of multivariate statistical methods needs to fully consider applicable conditions such as data characteristics.Through simulation experiments,students are encouraged to independently run simulation experiments,intuitively understand abstract multivariate concepts,and facilitate the understanding and application of multivariate statistical

关 键 词：模拟实验 多元统计 概念原理 教学 

分 类 号：G642[文化科学—高等教育学] R-4[文化科学—教育学]