Statistics and Data Analysis for Microarrays Using R and Bioconductor, 2nd Edition

Basic statistics in R 309

the values are not replace d. By default, size is equal to the size of x. Since

replace is also FALSE by default, simply calling sample(x) will generate a

random permutation of x. Finally, the parameter prob can be used to specify

a vector with the probabilities of picking individual elements from x.

Let us use this function to construct a sample representing 15 random

throws of an unbiased dice:

> x=1:6

> y=sample(x,15,replace=T)

> y

[1] 2 3 4 3 4 3 6 1 4 1 5 6 1 1 5

or 10 tosses of a coin that was biased such that the head is 10% more likely

than the tail:

> sample(c("h","t"),10,replace=T,c(0.6,0.4))

[1] "t" "t" "h" "h" "t" "t" "t" "h" "h" "h"

In practical data analysis, the function sample is often used in Monte-Carlo

type simulations ...