Confidence Intervals for Means

College Depth 75 in the knowledge graph I know this Set as goal
Unlocks 752 downstream topics
confidence-interval interval-estimation t-distribution

Core Idea

A confidence interval for a population mean is an interval (estimate ± margin of error) computed so that, in repeated sampling, it contains the true mean with a specified confidence level (typically 95%). For large samples, use the normal (z) distribution: x̄ ± z* × (s/√n). For smaller samples, use the t-distribution: x̄ ± t* × (s/√n). The confidence level describes the long-run proportion of intervals that capture the parameter, not the probability that the true mean lies in a specific computed interval.

How It's Best Learned

Compute confidence intervals for various sample sizes and confidence levels. Interpret them correctly in context. Observe that wider confidence levels produce narrower intervals and vice versa.

Common Misconceptions

Thinking a 95% CI means 95% probability the true mean is in the interval (it's fixed; the interval is random). Confusing confidence level with p-value. Misunderstanding how sample size affects margin of error.

Explainer

The Central Limit Theorem guarantees that for a large enough sample, the sample mean X̄ is approximately normally distributed with mean μ and standard deviation σ/√n, regardless of the population's shape. This is the fact that makes confidence intervals for means work. From your study of z-scores, you can standardize: the quantity (X̄ - μ)/(σ/√n) is approximately standard normal. Choosing z* = 1.96, we know P(-1.96 ≤ (X̄ - μ)/(σ/√n) ≤ 1.96) ≈ 0.95. Rearranging to isolate μ in the middle gives X̄ - 1.96(σ/√n) ≤ μ ≤ X̄ + 1.96(σ/√n) — the 95% confidence interval.

In practice σ is unknown, so substitute the sample standard deviation s. For large samples (n ≥ 30 is a common guideline), this substitution introduces negligible additional error and the z-interval X̄ ± 1.96(s/√n) applies. The quantity 1.96(s/√n) is the margin of error — half the interval width. Notice two things: the margin of error shrinks like 1/√n as sample size grows, and the multiplier 1.96 corresponds to 95% confidence. For 99% confidence use z* = 2.576, which widens the interval. More confidence requires a wider net.

For small samples, substituting s for σ introduces real additional uncertainty, and the distribution of (X̄ - μ)/(s/√n) is not exactly standard normal — it follows a t-distribution with n-1 degrees of freedom. The t-distribution has heavier tails than the normal, reflecting the extra uncertainty from estimating σ. The t-interval X̄ ± t*(s/√n) uses the appropriate t-critical value from a table. For n = 10 at 95% confidence, t* ≈ 2.26 (wider than 1.96). As n increases, the t-distribution approaches the normal and t* approaches z* = 1.96.

The correct interpretation is the most important thing to internalize. A computed interval like [3.2, 4.8] does not have "a 95% probability of containing μ." The true mean μ is a fixed number; it either lies in [3.2, 4.8] or it does not — probability does not apply to the specific interval in front of you. What 95% describes is the procedure: if you repeatedly drew samples and computed intervals by this method, 95% of those intervals would contain μ. Confidence is a property of the long-run procedure, not of any individual interval.

Practice Questions 5 questions

Prerequisite Chain

Counting to 10Counting to 20Understanding ZeroThe Number ZeroCounting to FiveOne-to-One CorrespondenceCombining Small Groups Within 5Addition Within 10Addition Within 20Two-Digit Addition Without RegroupingTwo-Digit Addition with RegroupingAddition Within 100Repeated Addition as MultiplicationMultiplication Facts Within 100Division as Equal SharingDivision as Grouping (Measurement Division)Division: Grouping (Repeated Subtraction) ModelDivision: Fair Sharing ModelDivision as Equal SharingDivision as GroupingBasic Division FactsDivision Facts Within 100Two-Digit by One-Digit DivisionDivision with RemaindersRemainders and Quotients in DivisionDivision Word ProblemsIntroduction to Long DivisionFactors and MultiplesPrime and Composite NumbersEquivalent FractionsRelating Fractions and DecimalsDecimal Place ValueReading and Writing DecimalsComparing and Ordering DecimalsAdding and Subtracting DecimalsMultiplying DecimalsDividing DecimalsDividing FractionsMixed Number ArithmeticOrder of OperationsInteger Order of OperationsVariable ExpressionsCombining Like TermsOne-Step EquationsTwo-Step EquationsSolving Multi-Step EquationsEquations with Variables on Both SidesAngle Pairs: Complementary, Supplementary, and VerticalParallel Lines and TransversalsCorresponding AnglesAlternate Interior AnglesTriangle Angle Sum TheoremExterior Angle TheoremTriangle Inequality TheoremSimilar Triangles: AA SimilaritySimilar Triangles: SSS and SAS SimilarityProportions in Similar TrianglesRight Triangle Trigonometry IntroductionTrigonometric Ratios ReviewRadian MeasureConverting Between Degrees and RadiansThe Unit CircleGraphing Sine and CosineGraphing Tangent and Reciprocal Trigonometric FunctionsDerivatives of Trigonometric FunctionsAntiderivativesIndefinite IntegralsBasic Integration RulesRiemann SumsDefinite Integral DefinitionProbability Density Functions and Continuous DistributionsCumulative Distribution FunctionsContinuous Random VariablesNormal DistributionCentral Limit TheoremConfidence Intervals for Means

Longest path: 76 steps · 364 total prerequisite topics

Prerequisites (2)

Leads To (4)