Central Limit Theorem

central_limit_theorem.R

## look at dataframe diamonds
library(tidyverse)
glimpse(diamonds)

## assume this is all prices (population)
pop_prices <- diamonds$price

## sample n=30, repeats 1000 times
sam_prices <- replicate(
  1000, mean(sample(pop_prices, size = 30))
)

## check if the mean of sample means is close to the population mean
summary(pop_prices)
summary(sam_prices)

## look at the histogram
hist(sam_prices, xlim = c(1000, 7000))

## let's change line 10, size=1000. Look at the histogram again.