FRM Exam Part I · Sample Moments

Sample Mean and Its Properties for FRM Part I

Updated 11 October 2026 · Fact-checked

The sample mean is the sum of n observations divided by n. It is an unbiased estimator of the population mean, so E(X̄) = μ. Its standard error is σ ÷ √n, or s ÷ √n when σ is unknown. For large n, the central limit theorem makes X̄ approximately normal.

Understand Sample Mean and Its Properties

The sample mean X̄ is the average of the n values you observe. You use it to estimate the unknown population mean μ. Different samples give different averages, so X̄ is itself a random variable.

Because X̄ is random, it has its own distribution, called the sampling distribution. If observations are independent and identically distributed (i.i.d.) with mean μ and variance σ², then E(X̄) = μ and Var(X̄) = σ² ÷ n. The first result means X̄ is unbiased: on average it hits the target. This holds for any n, and for any distribution with a finite mean.

The standard error is the standard deviation of X̄: σ ÷ √n. It measures how far a sample mean typically lands from μ. It is not the standard deviation of the data. It shrinks as n grows, but only with the square root. To halve the standard error, you need four times the data.

If the data are normal, X̄ is exactly normal for any n. If not, the central limit theorem says X̄ is approximately normal for large n, provided the variance is finite. That lets you build confidence intervals and run tests on means.

In practice σ is usually unknown, so you replace it with the sample standard deviation s. The estimated standard error is s ÷ √n. Tests then use the t distribution when the data are roughly normal and n is small.

Key formulas to remember

Sample mean: X̄ = (1 ÷ n) × Σ Xᵢ, for i = 1 to n; Add all observations and divide by n.
Unbiasedness: E(X̄) = μ; Holds for i.i.d. data with finite mean, for any sample size.
Variance of the sample mean: Var(X̄) = σ² ÷ n; Requires independent observations with common variance σ².
Standard error (σ known): SE = σ ÷ √n; Standard deviation of X̄.
Estimated standard error: SE = s ÷ √n; Use when σ is unknown; s uses n − 1 in the denominator.
Standardised sample mean: Z = (X̄ − μ) ÷ (σ ÷ √n); Approximately standard normal by the CLT for large n.
Confidence interval for the mean: X̄ ± critical value × SE; Use z for large samples or known σ; t with n − 1 degrees of freedom otherwise.

How to solve Sample Mean and Its Properties questions

Use this sequence for any question on the sample mean, its standard error or its distribution.

1Identify what is given: n, the sample mean or data, and whether you have σ (population) or s (sample).
2If raw data are given, compute X̄ = Σ X ÷ n.
3Compute the standard error: σ ÷ √n if σ is known, otherwise s ÷ √n.
4Decide the distribution: normal data gives a normal X̄; otherwise rely on the CLT if n is large.
5Standardise: Z = (X̄ − μ) ÷ SE, or build the interval X̄ ± critical value × SE.
6Read the probability or critical value from the normal or t table; use t with n − 1 degrees of freedom for small samples with unknown σ.
7Check the answer is sensible: the SE must be smaller than the data's standard deviation.

Quickest way: Square-root-of-n scaling shortcut

When to use it: When a question asks how the standard error changes with sample size or asks for the sample size needed for a target precision.

SE is proportional to 1 ÷ √n, so the ratio of new SE to old SE is √(old n ÷ new n).
Quadrupling n halves SE; multiplying n by 9 cuts SE to one third.
For a target SE, solve n = (σ ÷ target SE)² and round up.
For a standard normal-based interval, remember 1.645, 1.96 and 2.576 for 90%, 95% and 99% two-sided intervals roughly (1.645 for 90%).

Common mistakes in Sample Mean and Its Properties

Using the data standard deviation as the standard error.
Both are called a standard deviation and the √n step is forgotten.
Fix: Always divide by √n when the question is about the mean.
Dividing by n instead of √n.
Confusing variance σ² ÷ n with standard error σ ÷ √n.
Fix: Variance of X̄ uses n; standard error is its square root, so it uses √n.
Saying a larger sample makes the sample mean 'more unbiased'.
Mixing up bias with precision.
Fix: X̄ is unbiased at every n. A larger n lowers the standard error, not the bias.
Claiming the CLT makes the data normal.
Misreading what becomes normal.
Fix: The CLT applies to the distribution of X̄, not to the individual observations.
Using z when σ is unknown and n is small.
Defaulting to the normal table.
Fix: Use s and the t distribution with n − 1 degrees of freedom unless n is large.
Ignoring autocorrelation in return data.
Assuming i.i.d. automatically.
Fix: The formula σ ÷ √n needs independence. Positive autocorrelation makes the true standard error larger.

Worked examples

Example 1

A risk analyst records 9 daily returns (in %): 1.2, −0.4, 0.8, 2.0, −1.0, 0.6, 1.4, 0.0, −0.2. Compute the sample mean, the sample standard deviation and the estimated standard error of the mean.

Show the solution

Sum = 1.2 − 0.4 + 0.8 + 2.0 − 1.0 + 0.6 + 1.4 + 0.0 − 0.2 = 4.4.
X̄ = 4.4 ÷ 9 = 0.4889%.
Deviations squared: (0.7111)² = 0.5057; (−0.8889)² = 0.7901; (0.3111)² = 0.0968; (1.5111)² = 2.2834; (−1.4889)² = 2.2168; (0.1111)² = 0.0123; (0.9111)² = 0.8301; (−0.4889)² = 0.2390; (−0.6889)² = 0.4746.
Sum of squares = 7.4488.
s² = 7.4488 ÷ 8 = 0.9311, so s = 0.9649%.
SE = 0.9649 ÷ √9 = 0.9649 ÷ 3 = 0.3216%.

Answer: X̄ ≈ 0.489%, s ≈ 0.965%, SE ≈ 0.322%.

Example 2

Monthly returns on a fund have a standard deviation of 4%. Assume i.i.d. returns. How many months of data are needed so the standard error of the mean return is at most 0.5%?

Show the solution

Set σ ÷ √n ≤ 0.5, with σ = 4.
√n ≥ 4 ÷ 0.5 = 8.
n ≥ 8² = 64.

Answer: At least 64 months of data.

Exam tips

Questions often test the distinction between standard deviation and standard error. Check which one the question asks for.
Expect conceptual items on unbiasedness: it holds for any n and does not need normality.
Watch for 'how does SE change' questions; use the √n scaling instead of recomputing.
Read whether σ or s is given before choosing z or t.
Arithmetic is light, so use the calculator's square root and statistics mode to save time.

Practice questions from Sample Moments

Sample Mean and Its Properties in other exams

The same ground in other exams, if you are preparing for more than one or want another angle on it.

Actuarial Core Principles (IAI)Sample Mean and Sample Variance

Sample Mean and Its Properties: frequently asked questions

Is the sample mean an unbiased estimator?

Yes. For i.i.d. observations with a finite mean, E(X̄) = μ at any sample size. Unbiasedness does not require normality.

How do you calculate the standard error of the mean?

Divide the standard deviation by the square root of n. Use σ if it is known, or the sample standard deviation s if not.

How does the central limit theorem relate to the sample mean?

For large n, the distribution of X̄ is approximately normal with mean μ and standard deviation σ ÷ √n. This holds whatever the shape of the data, provided the variance is finite.

What is the difference between standard deviation and standard error?

Standard deviation describes the spread of individual observations. Standard error describes the spread of the sample mean across repeated samples, and equals the standard deviation divided by √n.