几种相关系数辨析及其在R语言中的实现  

Discrimination of Several Correlation Coefficients and Their Implementation in R Software

作　　者：金林[1] 李研 JIN Lin;LI Yan(School of Statistics and Mathematics,Zhongnan University of Economics and Law,Wuhan 430073,China)

机构地区：[1]中南财经政法大学统计与数学学院,湖北武汉430073

出　　处：《统计与信息论坛》2019年第4期3-11,共9页Journal of Statistics and Information

基　　金：国家社会科学基金青年项目<广义可加模型及其应用>(14CTJ011)

摘　　要：对常见的Pearson简单相关系数、Spearman和Kendall等级相关系数、Cramer’s V系数、偏相关系数、广义相关测度、复相关系数、典型相关系数、广义相关系数和多向量间相关系数的适用条件、联系和区别等进行了辨析,给出了这些相关系数在R软件中的实现方法,并选取2016年中国31个省市的数据,对经济、能源和环境污染三方面进行相关分析,计算相关系数并解释其实际意义,最后对这些相关系数的基本情况进行了总结。We distinguish the application conditions,linkage and difference of Pearson correlation coefficient,Spearman and Kendall rank correlation coefficient,Cramer’s V coefficient,partial correlation coefficient,generalized measures of correlation,multiple correlation coefficient,canonical correlation coefficient,generalized correlation coefficient and multivariate correlation coefficient and then the implementation of these correlation coefficients are given in R software.After this,based on the data of 31 provinces in China in 2016,we select economy,energy and environmental pollution to calculate correlation coefficients and make some explanations of the results.Finally,this paper summarizes the basic conditions of these correlation coefficients.

关 键 词：简单相关 等级相关 广义相关测度 复相关 典型相关 广义相关 多向量相关 

分 类 号：F224.0[经济管理—国民经济] TP317[自动化与计算机技术—计算机软件与理论]