CODEWITHSUNDEEP
r
What
What

Reputation: 195

some misunderstanding with cut() function

I am turning my variables from discrete to continuous one. How can i now get the median values for each of my intervals.

sample <- c(30,16,12,40,14,30,5,5,5,5,38,30,45,22,30,31,22,35,45,29)
sample$Cut <- cut(sample,seq(min(sample),max(sample),(max(sample)-min(sample))/r),include.lowest = TRUE)

where my magical r value is

 r = log(length(sample), base = 2)
    r = trunc(r)
    r = r + 1

Now i need to get median values from each of this intervals:

[5,13] (13,21] (21,29] (29,37] (37,45] For this example i have to get 9,17,25,33,41.

Sorry for so silly question. Thank you in advance.

Upvotes: 1

Views: 76

Answers (1)

Zheyuan Li
Zheyuan Li

Reputation: 73265

You have break points:

b <- seq(min(sample), max(sample), (max(sample)-min(sample))/r)
# [1]  5 13 21 29 37 45

therefore the mid points for those intervals are:

(b[-length(b)] + b[-1]) / 2
# [1]  9 17 25 33 41

Upvotes: 1

Related Questions