现代统计图形 - 科学网—博客

70 第五章 图库
1 > par(mar = c(2, 2.5, 0.2, 0.1))
2 > x = rnorm(150)
3 > y = rnorm(50, 0.5)
4 > boxplot(list(x, y), names = c("x", "y"), col = 2:3,
5 + horizontal = TRUE, notch = TRUE, varwidth = TRUE)
6 > wilcox.test(x, y)
Wilcoxon rank sum test with continuity correction
data: x and y
W = 2579, p-value = 0.0009585
alternative hypothesis: true location shift is not equal to 0
x y
-2 -1 0 1 2 3
图 5.6: 箱线图的凹槽与统计推断:从凹槽不交叠的情况来看,两样本中位
数有显著差异。
2 > summary(insects.aov)
Df Sum Sq Mean Sq F value Pr(>F)
spray 5 2669 534 34.7