Mathematics · Statistics

Confidence interval and standard error of the mean

The t confidence interval quantifies sampling uncertainty in a mean when the population standard deviation is unknown.

AdvancedUniversity/collegeBachelor foundations

Create flashcards or a quiz I already have an account

Free to browse · flashcards or a multiple-choice quiz · import from Essential

Formula

\overset{x}{ˉ} \pm t_{1 - α /2, n - 1} \frac{s}{n}

x̄, s and interval endpoints have the measurement unit; the standard error has the same unit.

Variables & units

Variables & units
Symbol	Meaning	Unit
x̄	Sample mean	unit of the measured quantity
$s$	Sample standard deviation	unit of the measured quantity
$n$	Sample size	dimensionless
$t$	t quantile with n−1 degrees of freedom	dimensionless
$α$	Significance level; confidence level is 1−α	dimensionless

LaTeX

\bar{x} \pm t_{1-\alpha/2, n-1}\,\frac{s}{\sqrt{n}}

QUANTA STUDYquanta-study.de

Derivation & background

The standard error s/√n describes the variation of the estimated mean across repeated samples. Since the population standard deviation is unknown, use a t quantile with n−1 degrees of freedom. In repeated sampling, the interval procedure covers the true mean in about proportion 1−α of repetitions; a probability statement about the fixed mean for one computed interval is not correct.

Exam blueprint

Validity range

For independent normally distributed observations; with large samples the t method is often robust, but dependence and strong outliers remain problematic.

Derivation steps

For a normal population, the standardized sample-mean error follows a t distribution with n−1 degrees of freedom.

1Compute x̄ and s from the n observations.
2Find the t quantile and standard error s/√n; form x̄ ± t·SE.

Rearrangements

Report a confidence interval for a population mean

SE=\frac{s}{\sqrt{n}}

For independent normally distributed observations; with large samples the t method is often robust, but dependence and strong outliers remain problematic.

Task variant

n=25, x̄=10, s=4, 95%: SE=0.8 and t≈2.064, so the interval is [8.35,11.65].

For n=25, x̄=10, s=4 and 95% confidence, t_(0.975;24)≈2.064.
Standard error: 4/5=0.8.
Interval: 10±2.064·0.8=10±1.651, or [8.35,11.65].

Check: the half-width grows with s and shrinks with √n.

Common mistakes

Interpreting a confidence interval as a probability that the fixed parameter lies in this particular interval.

The confidence level describes the long-run coverage rate of the procedure over repeated samples.

Exam context

Measurement uncertainty, mean comparisons and sample-size planning.

Formula cluster

Statistical inference

The standard error measures precision of the mean; the t quantile scales it into an interval.

f(x) = 1/(σ√2π) · e^(−(x−μ)²/2σ²)

Normal Distribution (Gaussian Bell Curve)

σ = √Var(X)

Standard Deviation

μ±σ: 68,3 %, μ±2σ: 95,4 %, μ±3σ: 99,7 %

Sigma Rules (Sigma Intervals)

Worked example

For n=25, x̄=10, s=4 and 95% confidence, t_(0.975;24)≈2.064. Standard error: 4/5=0.8. Interval: 10±2.064·0.8=10±1.651, or [8.35,11.65]. Check: the half-width grows with s and shrinks with √n.

Applications

Summarizing measurements, comparing means and reporting sampling uncertainty in laboratory work, medicine or quality control.

How do you calculate with Confidence interval and standard error of the mean?

Here is how to work through a typical Confidence interval and standard error of the mean (x̄ ± t · s/√n) task step by step:

1
Task
n=25, x̄=10, s=4, 95%: SE=0.8 and t≈2.064, so the interval is [8.35,11.65].
Solution path
1. For n=25, x̄=10, s=4 and 95% confidence, t_(0.975;24)≈2.064.
2. Standard error: 4/5=0.8.
3. Interval: 10±2.064·0.8=10±1.651, or [8.35,11.65].
Check: the half-width grows with s and shrinks with √n.

Frequently asked questions about Confidence interval and standard error of the mean

What is the standard error?+

The standard error of the mean is s/√n. It estimates how much x̄ would vary from sample to sample. It is not the standard deviation of individual measurements, which is s. Four times as many observations approximately halve the standard error because √n is in the denominator. The standard deviation describes the spread of individual observations around their mean. The standard error describes the spread of the estimated mean across repeated samples. They share units but answer different questions and should not be confused in reports or error bars.

Why is the t distribution needed?+

When population σ is unknown, s is estimated from the same sample. This extra uncertainty makes the tails wider than when σ is known. The t distribution accounts for this and approaches the normal distribution as n grows. For small samples its critical value is therefore noticeably larger than 1.96. With few degrees of freedom, the t distribution has heavier tails because s is itself estimated from random data. As n grows, this extra uncertainty shrinks and the t quantile approaches the normal quantile. Thus 1.96 should not be used automatically, especially for very small samples.

What does a 95 percent confidence interval mean?+

If many comparable samples were drawn and an interval computed each time by the same method, about 95% of those intervals would contain the fixed population mean. A particular interval either contains it or does not. The 95% is the procedure’s long-run coverage, not a posterior probability for the parameter. The confidence level describes how reliably the construction method works over repeated samples. Once the data are observed, the interval is fixed. A Bayesian probability for the parameter requires a different model and an explicit prior; the interpretations are not interchangeable.

How does sample size affect interval width?+

The half-width is t·s/√n. With s and confidence level fixed, it falls by about √2 when n doubles. To halve the uncertainty, roughly four times the sample size is needed. More data help, but do not remove systematic measurement error. The square root explains the diminishing return of additional observations. A fourfold sample size approximately halves the standard error when spread is similar. This assumes independent observations: repeated measurements from one person or correlated time points provide less new information than the same number of independent cases.

When is this formula unsuitable?+

It assumes independent observations and a meaningful mean model. With autocorrelated time series, strongly skewed small samples or dominating outliers, the standard error can mislead. If population spread is known, use a z interval; proportions need a binomial-proportion interval. Before calculating, inspect the study design and a plot of the data. An extreme outlier can strongly shift x̄ and s; dependence can make the standard error too small. With strong skew and small n, robust methods or a suitable bootstrap may help if their assumptions are appropriate.

Quanta exam set

Curated exam set for "Confidence interval and standard error of the mean":

Question (front)

Which formula describes Confidence interval and standard error of the mean?

Answer in your set

Question (front)

How do you rearrange Confidence interval and standard error of the mean for Report a confidence interval for a population mean?

Answer in your set

Question (front)

Which common mistake happens with Confidence interval and standard error of the mean?

Answer in your set

+ 8 more cards: units, variables, derivation, example, exam task

The formula set contains 11 cards. After importing, review them and start practicing; your ratings determine later review intervals.

Create flashcards or a quiz I already have an account

Subject references and further reading

This list names subject references and further reading. A page or section number appears when it is part of the reference; these are not verbatim quotations.

[1]NIST/SEMATECH e-Handbook, §1.3.5.2: Confidence Limits for the Mean

Related formulas

\hat\theta_{ML}=\arg\max_{\theta\in\Theta}L(\theta\mid x_1,\ldots,x_n)

Maximum Likelihood Estimation

More formulas: Probability and statistics

P(A|B) = \frac{P(B|A) \cdot P(A)}{P(B)}

Bayes' Theorem

P(X = k) = \binom{n}{k} \cdot p^{k} \cdot (1-p)^{n-k}

Binomial Distribution

E(X) = \mu = \sum_{i} x_{i} \cdot p_{i}

Expected Value

P(A \mid B) = \frac{P(A \cap B)}{P(B)} \quad (P(B) > 0)

Conditional Probability

Spaced-repetition apps

Compare scheduling workflows

Study evidence

Read methods, results and limits

Compare flashcard apps

FSRS support and study features

Create a formula exam set

From Essential in Quanta

Retain Confidence interval and standard error of the mean for exams

Create a curated FSRS exam set for x̄ ± t · s/√n: formula recall, variables, derivation, rearrangement, worked example, common mistakes and exam context.

Create flashcards or a quiz Already registered? Continue directly

Curated formula set · LaTeX · FSRS spaced repetition · import from Essential

Quanta Study editorial team

Symbol

Meaning

Unit

x̄

Sample mean

unit of the measured quantity

s

Sample standard deviation

unit of the measured quantity

n

Sample size

dimensionless

t

t quantile with n−1 degrees of freedom

dimensionless

α

Significance level; confidence level is 1−α

dimensionless

Derivation & background

Exam blueprint

Validity range

For independent normally distributed observations; with large samples the t method is often robust, but dependence and strong outliers remain problematic.

Derivation steps

For a normal population, the standardized sample-mean error follows a t distribution with n−1 degrees of freedom.

1Compute x̄ and s from the n observations.
2Find the t quantile and standard error s/√n; form x̄ ± t·SE.

How do you calculate with Confidence interval and standard error of the mean?

Here is how to work through a typical Confidence interval and standard error of the mean (x̄ ± t · s/√n) task step by step:

Task

n=25, x̄=10, s=4, 95%: SE=0.8 and t≈2.064, so the interval is [8.35,11.65].

Solution path

For n=25, x̄=10, s=4 and 95% confidence, t_(0.975;24)≈2.064.
Standard error: 4/5=0.8.
Interval: 10±2.064·0.8=10±1.651, or [8.35,11.65].

Check: the half-width grows with s and shrinks with √n.

Frequently asked questions about Confidence interval and standard error of the mean

What is the standard error?+

Why is the t distribution needed?+

What does a 95 percent confidence interval mean?+

How does sample size affect interval width?+

When is this formula unsuitable?+

Retain Confidence interval and standard error of the mean for exams

Create a curated FSRS exam set for x̄ ± t · s/√n: formula recall, variables, derivation, rearrangement, worked example, common mistakes and exam context.

Curated formula set · LaTeX · FSRS spaced repetition · import from Essential