r - 在进行 Wilcoxon 测试之前我需要缩放吗？

Question

我正在对我的数据进行 Wilcoxon 秩和检验。数据的单位不同，尺度也大不相同。在运行测试之前我需要输入这个命令吗？

## where x is my data frame
scale(x, center = TRUE, scale = TRUE)

还是 Wilcoxon 秩和检验本身就是这样做的？

Answer 1

您无法缩放，因为 Wilcoxon 是一个位置测试（R 中的默认值是 mu=0），如果您缩放数据，您将丢失真实的位置信息。

> x <- rnorm(100,700,20)
> 
> wilcox.test(x) # Mu = 0

        Wilcoxon signed rank test with continuity correction

data:  x 
V = 5050, p-value < 2.2e-16
alternative hypothesis: true location is not equal to 0 

> wilcox.test(x,mu=mean(x))

        Wilcoxon signed rank test with continuity correction

data:  x 
V = 2650, p-value = 0.6686
alternative hypothesis: true location is not equal to 697.4377 

> wilcox.test(scale(x))  # Mu = 0

        Wilcoxon signed rank test with continuity correction

data:  scale(x) 
V = 2650, p-value = 0.6686
alternative hypothesis: true location is not equal to 0