要在R中执行相关性测试，我们需要使用带有两个变量的cor.test函数，并且该函数会返回许多值，例如测试统计值，自由度，p值，置信区间和相关系数值。如果要从相关测试输出中提取相关系数值，则可以使用估计函数，如以下示例所示。
x1<-rnorm(20,5,2) y1<-rnorm(20,5,1) cor.test(x1,y1)
输出结果
Pearson's product-moment correlation data: x1 and y1 t = -0.13423, df = 18, p-value = 0.8947 alternative hypothesis: true correlation is not equal to 0 95 percent confidence interval: -0.4675990 0.4167308 sample estimates: cor -0.03162132
cor.test(x1,y1)$估计cor -0.08194057
x2<-runif(5000,2,5) y2<-runif(5000,2,10) cor.test(x2,y2)
输出结果
Pearson's product-moment correlation data: x2 and y2 t = -1.4823, df = 4998, p-value = 0.1383 alternative hypothesis: true correlation is not equal to 0 95 percent confidence interval: -0.048653479 0.006760764 sample estimates: cor -0.02096246
cor.test(x2,y2)$估计cor 0.01301688
x3<-runif(50,2,5) y3<-runif(50,2,10) cor.test(x3,y3)
输出结果
Pearson's product-moment correlation data: x3 and y3 t = -0.80709, df = 48, p-value = 0.4236 alternative hypothesis: true correlation is not equal to 0 95 percent confidence interval: -0.3817626 0.1680496 sample estimates: cor -0.1157106
cor.test(x3,y3)$估计cor 0.1031475
x4<-rexp(500,2.1) y4<-rexp(500,5.75) cor.test(y4,y4)
输出结果
Pearson's product-moment correlation data: y4 and y4 t = Inf, df = 498, p-value < 2.2e-16 alternative hypothesis: true correlation is not equal to 0 95 percent confidence interval: 1 1 sample estimates: cor 1
cor.test(y4,y4)$估计cor 1
x5<-rpois(100000,2) y5<-rpois(100000,5) cor.test(y5,y5)
输出结果
Pearson's product-moment correlation data: y5 and y5 t = 1.5006e+10, df = 99998, p-value < 2.2e-16 alternative hypothesis: true correlation is not equal to 0 95 percent confidence interval: 1 1 sample estimates: cor 1
cor.test(y5,y5)$估计cor 1