data(anscombe)
cor(anscombe$x1, anscombe$y1)
## [1] 0.8164205
cor(anscombe$x2, anscombe$y2)
## [1] 0.8162365
cor(anscombe$x3, anscombe$y3)
## [1] 0.8162867
cor(anscombe$x4, anscombe$y4)
## [1] 0.8165214
plot(anscombe$x1, anscombe$y1, col=blues9, pch = 16, xlab = "x1", ylab = "y1")
plot(anscombe$x2, anscombe$y2, col=blues9, pch = 16, xlab = "x2", ylab = "y2")
plot(anscombe$x3, anscombe$y3, col=blues9, pch = 16, xlab = "x3", ylab = "y3")
plot(anscombe$x4, anscombe$y4, col=blues9, pch = 16, xlab = "x4", ylab = "y4")
雖然四組數據的相關係數都還蠻相近,但從圖形即可看出其相關的不同。在(x1,y1)這組,各點較為分散,沒有凝聚在回歸線上,則其相關性較低,但仍看得出是正相關;在(x2,y2)這組,各點較上組集中,但還是沒有很凝聚在回歸線上,則其相關性仍低,但仍看得出是正相關;在(x3,y3)這組,各點更為集中,且有凝聚在回歸線上,則其相關性偏高,且為正相關,但在圖表上方有出現沒有和其他點聚集的資料,擇期應是數據中的極端變項,去除後結果會更為精確;在(x4,y4)這組,各點雖然集中,但沒有很凝聚在回歸線上,反而聚集在圖表最左方,則其相關性雖高,但應是零相關。