Simulate a set of number less than 20 that follows normal distribution

Question

What can I do to compel R to give me a sample less than 20, such that the sample will have mean = 0 and variance = var.

MWE

rnorm(20, mean=0, sd=1)

As the sample size gets larger, the sample gets closer to normal. How then can I make R to give me a sample of n < 20 with a mean equal to zero and variance equal to whatever I specify?

not clear what you're asking: do you mean `rnorm(20, mean=0, sd=sqrt(var))` ... ???? — Ben Bolker, Feb 02 '20 at 21:45

score 4 · Answer 1 · answered Feb 02 '20 at 21:56

Try

rnorm(20, mean=0, sd=sqrt(var))

For what it's worth

your last paragraph sounds like a slightly confused statement of the Central Limit Theorem; there's no difficulty in creating small data sets that are normal, or Gaussian (the CLT says that sums of N independent, identically distributed variables approach normality as N goes to infinity ...)
it would be worth using v rather than var to denote your variance, since var() is a built-in function in R (this is mostly harmless, but occasionally confusing).

y<-rnorm(20, mean=0, sd=sqrt(1)); mean(y); [1] 0.20924 – Daniel James Feb 02 '20 at 22:05 — Daniel James, Feb 02 '20 at 22:05

Simulate a set of number less than 20 that follows normal distribution

1 Answers1