Definition

It is a specific type of Sampling Distribution

Let 𝑋 be a probability function 𝑓(𝑥), mean 𝜇 and variance 𝜎2, then the Sampling Distribution of the mean is:

𝑋=1𝑛∑𝑛𝑖=1𝑋𝑖, where:𝜇𝑋=𝜇 and 𝜎2𝑋=𝜎2𝑛

Normal Approximation

Independence

For a sufficiently large 𝑛, we can apply the Central Limit Theorem

𝑋=𝑁(𝜇,𝜎√𝑛)→𝑍=(𝑋−𝜇)√𝑛𝜎

This applies when:

  • 𝑛≥30
  • 𝑋 has a Normal Distribution

No Independence

When the population is finite and we have a Sampling without replacement, then we follow a Hypergeometric Distribution.

𝜇𝑋=𝜇 and 𝜎2𝑋=𝜎2𝑛(𝑁−𝑛𝑁−1)

And therefore:

𝑋=𝑁(((𝜇,√𝜎2𝑛(𝑁−𝑛𝑁−1))))→𝑍=𝑋−𝜇𝜎√𝑛√𝑁−𝑛𝑁−1

Solution Methods

Normal Population

𝑋=𝑁(𝜇,𝜎√𝑛)→𝑍=(𝑋−𝜇)√𝑛𝜎

In R:

pnorm(x, μ, σ/sqrt(n))

Normal Population, n > 30, but sigma unknown

𝑇(𝑛−1)=𝑋−𝜇𝑆/√𝑛

In R:

t_calc = (smu - mu) / (S / sqrt(n))
pt(t_calc, df = n-1)