相关性检验（二维列联表相关 协方差 Pearson相关 Spearman相关 相关性检验 相关可视化）

相关

二维列联表相关

data <- xtabs(~Treatment+Improved, data = Arthritis) ## 生成二维列联表

assocstats(data)

协方差

states <- state.x77[,1:6]
cov(states)

Pearson相关

cor(states)

x <- states[,c("Population","Income","Illiteracy","HS Grad")]
y <- states[,c("Life Exp","Murder")]
cor(x,y)

Spearman相关

cor(states,method = "spearman")

相关性检验

cor.test(states[,1],states[,2],alternative = "two.side",method = "spearman") ## 只能计算单个变量相关

library(psych)

corr.test(states,use = "complete")  ## use 表示对缺失值的成行删除

corr.test(states,use = "pairwise")  ## use 表示对缺失值的成对删除

pcor(c(1,5,2,3,6),cov(states))     

pcor.test(pcor(c(1,5,2,3,6),cov(states)) ,c(2,3,6),50)   ## 偏相关检验，c(2,3,6)代表要控制的变量，50代表样本量

相关可视化

library(corrplot)
res <- cor(states)

cols <- colorRampPalette(c("red", "white", "blue"))
corrplot.mixed(res,lower.col = cols(100),upper.col = cols(100),tl.pos="lt",tl.col="black")