Chapter 7 · OpenStax Ch 7
The Central Limit Theorem
Why averages of almost anything look normal, and how their spread shrinks with n.
7.1 CLT for sample means
Pick an ugly parent distribution. Skewed, two-humped and U-shaped all work. Draw a sample of \(n\) values from it and compute their mean. Do it again, and again. The central limit theorem says the pile of sample means turns into a normal curve as \(n\) grows. The shape of the parent does not matter. Its centre is the parent mean \(\mu\), and its spread is \(\sigma/\sqrt{n}\).1
Start with \(n = 1\), where the pile of “means” is just the parent again. Slide \(n\) to 5, then 30, and keep drawing. The orange curve is not fitted to the data. It is the theorem's prediction, drawn before a single sample is taken. Two humps, a long tail, a U shape. All melt into the same bell. That is why averages of almost anything are normal.
1 The SD of sample means shown is the sample standard deviation, dividing by \(n - 1\). Reading: OpenStax Introductory Statistics, Section 7.1.
Try it
- Skewed is the parent and Sample size, n is 5.
- Press Draw 1 sample. Five dots appear and their mean drops into the lower histogram.
- Press Draw 100 several times. The means pile into a bell, even though the parent is lopsided.
- Compare SD of sample means with σ/√n. They agree.
- Slide n to 30, press Reset, and draw again. The bell is narrower. Try U-shaped or Die for other parents.
7.2 The standard error
How much does a sample mean wander? The standard error of the mean is the standard deviation of the sampling distribution,
\[\sigma_{\bar{x}} = \frac{\sigma}{\sqrt{n}},\]
so it shrinks with the square root of the sample size. Four times as much data buys only half the spread, and a hundred times as much buys a tenth. Lock a parent and press “Sweep all n”. Each dot is the standard deviation of two thousand simulated sample means at one value of \(n\), and the curve is \(\sigma/\sqrt{n}\). The dots sit on the curve for every parent, because the formula does not care about the shape, only about \(\sigma\). The lower chart shows the pile of means at the chosen \(n\) tightening around \(\mu\).
Reading: OpenStax Introductory Statistics, Sections 7.1, 7.3.
Try it
- Flat is the parent and Sample size, n is 4.
- Press Simulate at this n. 2000 sample means are drawn and their SD becomes a dot on the chart.
- Compare SD of 2000 sample means with Standard error σ/√n.
- Press Sweep all n. Twelve dots appear along the σ/√n curve, from n = 1 to 100.
- Pick Skewed or Two humps and sweep again. The dots still follow the curve, because only σ matters.
7.3 CLT for sums
Adding instead of averaging changes nothing about the shape. The sum of \(n\) draws is \(n\) times their mean. So it too becomes normal as \(n\) grows, with
\[\text{mean} = n\mu, \qquad \text{SD} = \sigma\sqrt{n}.\]
The sum's spread grows with \(n\), while the mean's spread shrinks, and both facts come from the same \(\sqrt{n}\). Roll ten dice and add them up, many times. Single rolls are flat from 1 to 6, yet the totals pile into a bell around 35. Slide \(n\) up and the axis widens to follow \(n\mu \pm 5\sigma\sqrt{n}\), but the bell keeps its shape. This is the theorem behind why measurement errors, which are sums of many small nudges, are so often normal.
Reading: OpenStax Introductory Statistics, Section 7.2.
Try it
- Die is the parent and Number of draws added, n is 10, so each sum is ten dice.
- Press Draw 1 sum a few times. Single sums land near 35.
- Press Draw 100 several times. The sums form a bell around nμ.
- Compare SD of sums with σ√n. They agree.
- Slide n to 50. The axis widens, because a sum's spread grows with √n while a mean's shrinks.
Why the standard error is σ/√n
Transcript
Why the standard error is σ/√n.
Take n independent draws from one population. Each draw has variance σ².
Variances of independent draws add. Var(X₁ + ⋯ + Xₙ) = σ² + ⋯ + σ² = nσ².
The mean is the sum divided by n. Dividing by n divides the variance by n². Var(X̄) = nσ²/n² = σ²/n.
Take the square root. The spread of the mean is σ over root n. SD(X̄) = σ/√n.
Here are 2000 sample means at each n, drawn from a flat population. The pile narrows.
n = 1: SD of means 2.88, σ/√n 2.89.
n = 4: SD of means 1.45, σ/√n 1.44.
n = 16: SD of means 0.74, σ/√n 0.72.
n = 64: SD of means 0.36, σ/√n 0.36.
Quadruple n and the spread halves. The square root is why.