As the title says, how does the following come about:

set.seed(1)  # for reproducibility
x <- rnorm(30, 10, 2)

mean(x)
# [1] 10.16492
mean(scale(x, center=FALSE))
# [1] 0.9678482

CodePudding user response：

?scale explains all: "scaling is done by dividing the (centered) columns of x by their standard deviations if center is TRUE, and the root mean square otherwise."

We can show that scaling by the RMS is what actually happened:

rms = sqrt(sum(x^2)/(length(x)-1))
mean(x)/rms
# [1] 0.9678482