What Is the Sampling Distribution of the Sample Mean?
When you repeatedly draw random samples of size n from a population and compute each sample's mean, those means form their own distribution — the sampling distribution of the sample mean. This calculator finds its center (the mean) and its spread (the standard error) from three inputs: the population mean μ, the population standard deviation σ, and the sample size n.
How to Use This Calculator
Enter the population mean (μ), the population standard deviation (σ), and your sample size (n). The tool returns the mean of the sampling distribution (μx̄), the standard error (σx̄), and the variance of the sample mean (σx̄²). The standard error tells you how much sample means typically vary from the true population mean.
The Formula Explained
The mean of the sampling distribution always equals the population mean: \(\mu_{\bar{x}} = \mu\). The spread shrinks as samples get larger: \(\sigma_{\bar{x}} = \sigma/\sqrt{n}\). Because we divide by the square root of n, doubling the sample size does not halve the standard error — you must quadruple n to cut the standard error in half. By the Central Limit Theorem, for large n this distribution is approximately normal regardless of the population's shape.
$$\mu_{\bar{x}} = \text{Mean } \mu \qquad \sigma_{\bar{x}} = \frac{\text{Std Dev } \sigma}{\sqrt{\text{Sample Size } n}}$$
Worked Example
Suppose μ = 100, σ = 15, and n = 25. Then \(\mu_{\bar{x}} = 100\), and
$$\sigma_{\bar{x}} = \frac{15}{\sqrt{25}} = \frac{15}{5} = 3$$The variance is \(\sigma_{\bar{x}}^{2} = 3^{2} = 9\). So sample means of 25 observations cluster around 100 with a standard error of 3.
How Sample Size Changes the Standard Error
The table fixes the population mean at \(\mu = 100\) and the population standard deviation at \(\sigma = 15\), then varies the sample size \(n\). The mean of the sampling distribution stays at 100 in every row. Only the spread changes.
| Sample size n | Standard error \(\sigma/\sqrt{n}\) | Variance \(\sigma^2/n\) | SE as a ratio of σ |
|---|---|---|---|
| 1 | 15 | 225 | 1 |
| 4 | 7.5 | 56.25 | 0.5 |
| 9 | 5 | 25 | 0.3333 |
| 25 | 3 | 9 | 0.2 |
| 100 | 1.5 | 2.25 | 0.1 |
| 400 | 0.75 | 0.5625 | 0.05 |
The ratio of the standard error to σ equals \(1/\sqrt{n}\). Because of the square root, quadrupling the sample size halves the standard error: going from n = 1 to 4, 4 to 16 (or 25 to 100, 100 to 400), the standard error is cut in half each time. Cutting it to one tenth requires 100 times as many observations, so there are diminishing returns from collecting more data.
Interpreting the Standard Error
The standard error \(\sigma_{\bar{x}} = \sigma/\sqrt{n}\) measures how much sample means vary from sample to sample. If the sampling distribution of \(\bar{x}\) is approximately normal (by the Central Limit Theorem, or because the population itself is normal), then about:
- 68% of sample means fall within 1 standard error of μ,
- 95% fall within 2 standard errors (more precisely, 1.96),
- 99.7% fall within 3 standard errors.
Example: with \(\mu = 100\) and \(\sigma_{\bar{x}} = 3\) (for instance σ = 15 and n = 25):
| Coverage | Interval | Range of sample means |
|---|---|---|
| ≈ 68% | \(100 \pm 1(3)\) | 97 to 103 |
| ≈ 95% | \(100 \pm 2(3)\) | 94 to 106 |
| ≈ 99.7% | \(100 \pm 3(3)\) | 91 to 109 |
Standard error vs. standard deviation. The population standard deviation σ describes how individual values vary around μ. The standard error describes how sample means vary around μ. It is always smaller than σ when n > 1, and it shrinks as n grows.
Normality and sample size. A common rule of thumb says n ≥ 30 is enough for the sampling distribution of the mean to be approximately normal. This is only a guideline: for roughly symmetric populations a smaller n may suffice, while for strongly skewed or heavy-tailed populations you may need considerably more.
Finite populations. The formula σ/√n assumes sampling with replacement or a very large population. When sampling without replacement and the sample is more than about 5% of a population of size N, the standard error is multiplied by the finite population correction \(\sqrt{\frac{N-n}{N-1}}\), which makes it smaller. This calculator does not apply that correction.
Key Terms and Symbols
- Population mean (μ): the average of all values in the population.
- Population standard deviation (σ): the typical distance of individual values from μ in the population.
- Sample size (n): the number of observations in each sample.
- Sample mean (x̄): the average of the n observations in one sample; it varies from sample to sample.
- Sampling distribution: the probability distribution of a statistic (here x̄) over all possible samples of size n from the population.
- Mean of the sampling distribution (\(\mu_{\bar{x}}\)): the expected value of x̄, which equals μ, so the sample mean is an unbiased estimator of μ.
- Standard error (\(\sigma_{\bar{x}}\)): the standard deviation of the sampling distribution of x̄, equal to \(\sigma/\sqrt{n}\).
- Variance of the sample mean (\(\sigma_{\bar{x}}^2\)): the square of the standard error, \(\sigma^2/n\).
- Central Limit Theorem: for independent observations from a population with finite variance, the sampling distribution of x̄ approaches a normal distribution as n increases, regardless of the population's shape.
FAQ
Why does the standard error get smaller with larger samples? Larger samples average out random fluctuations, so their means are more tightly packed around the true mean.
Does the population need to be normal? Not for the formulas here. The mean and standard error are exact for any population. Normality of the sampling distribution holds approximately for large n via the Central Limit Theorem.
What if I only have the sample standard deviation? If σ is unknown, use the sample standard deviation s as an estimate; the standard error becomes \(s/\sqrt{n}\), often used with the t-distribution.