Central Limit Theorem Simulator – See Sample Means Turn Normal in 3 Easy Steps
Central Limit Theorem Simulator
Free central limit theorem simulator – visualize how the distribution of sample means approaches a normal distribution, regardless of the population shape.
Population Parameters
The simulator will draw random data points from this underlying population shape.
Sampling Strategy
...
Use this free central limit theorem simulator to see with your own eyes why sample means follow a normal curve.
Quick answer
The central limit theorem says that if you take many random samples of size n and plot their means, the means form a roughly normal distribution – even when the population is not normal – with mean μ and standard error σ ÷ √n. Example: an exponential population with μ = 50 and σ = 50, samples of n = 30, gives an expected standard error of 50 ÷ √30 ≈ 9.13; this central limit theorem simulator produced a mean of 49.85 and spread of 9.21 from 1,000 samples.
Table of Contents
The central limit theorem (CLT) is the reason confidence intervals, t-tests and opinion polls work. But in a textbook it is just a sentence. Seeing it happen makes it click.
Our free central limit theorem simulator draws random samples from a uniform, right-skewed exponential or normal population, calculates each sample’s mean, and plots a histogram of those means. Increase the sample size and watch the bell curve get narrower and smoother.
What the Central Limit Theorem Says
- Take repeated random samples of the same size n from a population with mean μ and standard deviation σ.
- The distribution of the sample means is approximately normal when n is large enough (often n ≥ 30).
- Its centre is the population mean μ.
- Its spread (standard error) is σ ÷ √n, so larger samples give tighter estimates.
Effect of Sample Size
| Sample size n | Standard error (σ = 50) | Shape of the means |
|---|---|---|
| 5 | 22.36 | Still skewed for an exponential population |
| 30 | 9.13 | Close to normal |
| 100 | 5.00 | Very close to normal and narrow |
How to Use the Central Limit Theorem Simulator
Run your own experiment in three steps.
Step 1: Choose the Population and Sampling Settings
Pick a Parent Distribution – Uniform, Exponential (right-skewed) or Normal. Set the Sample Size (n) and the Number of Samples, e.g. n = 30 and 1,000 samples, then click Run Simulation.
Step 2: Watch the Distribution of Sample Means
The histogram shows the means of all your samples. Even from a skewed exponential population, they pile up into a bell shape around the population mean.
Step 3: Compare Simulation With Theory
The statistics panel compares the theoretical mean and expected standard error with the simulated mean and simulated standard deviation. Run it again with a different n to see the standard error shrink.
Why the Central Limit Theorem Matters
- Confidence intervals: we can say “the mean is 49.8 ± 1.96 × SE” because means are normally distributed.
- Hypothesis tests: z-tests and t-tests rely on the sampling distribution being approximately normal.
- Quality control: average measurements from production batches follow a predictable pattern.
- Polls and surveys: margins of error come from the same idea.
Experiments to Try
- Use the Exponential population with n = 2, then n = 30 – compare the shapes.
- Keep n = 30 and change the number of samples from 100 to 5,000 – the histogram gets smoother, but the spread stays about the same.
- Switch to a Uniform population – the means become normal even faster.
Next, calculate probabilities with the Normal Distribution Calculator or standardise values with the Z-Score Calculator.
Frequently Asked Questions
What is the central limit theorem in simple words?
If you average enough random samples, the averages follow a bell-shaped normal curve, whatever the shape of the original data.
How large should the sample size be?
A common rule of thumb is n ≥ 30, but very skewed populations may need more, and symmetric ones need less.
What is the standard error?
It is the standard deviation of the sample means, equal to σ ÷ √n.
Does the population need to be normal?
No. That is the power of the CLT – it works for uniform, skewed and many other distributions.
Why does my simulated value differ slightly from theory?
Simulations use random samples, so small differences are normal and shrink as you run more samples.
Is the central limit theorem simulator free?
Yes. It is free, runs in your browser and needs no sign-up.