Refresh KidLearning
LESSON 06 / 20 · TOPIC 4.3

What does confidence say about the population average?

You will be able to: Interpret coverage and evaluate a claimed mean without overstating certainty.

Graphs, tables and mathematical reasoningFree study resourceReview editionTeacher review pending

What does confidence say about the population average?

A 95% interval for average club travel time is (18,22) minutes. A claim of a 20-minute mean is compatible with that interval; a claim of 25 minutes is not.

A useful starting point: Why should before-and-after measurements stay paired? →

Words and symbols before equations

Confidence level
The method’s long-run fraction of intervals capturing the fixed parameter.
Compatible value
A parameter value inside the computed interval.
Population mean
The fixed average being estimated.
Repeated sampling
New random samples of the same size from the same population.
First 20 of 100 intervals; vertical line is true μ=201234567891011121314151617181920151719212325Mean time (minutes); interval row numbers at left
Read this model snapshot. 96 of 100 intervals capture μ=20 minutes at nominal 95% confidence. A finite run does not guarantee the nominal percentage.
What this picture assumes

100 independent simulated samples from a normal population with μ=20 and σ=5 minutes. Each interval estimates σ with its own s and uses t with n−1 df. All 100 intervals enter the table and capture count; the picture shows the first 20. Finite simulation coverage need not equal the confidence level.

Read the picture in three steps

  1. Read the axes and labels first. Identify what each symbol and line represents. Read the units and fixed conditions before comparing quantities.
  2. 96 of 100 intervals capture μ=20 minutes at nominal 95% confidence. A finite run does not guarantee the nominal percentage.
  3. Check what the picture assumes below. Use the Explore task to predict one change before moving a control.

Connect the picture to the mathematics

A contextual interpretation is: we are 95% confident that the population mean travel time lies between 18 and 22 minutes. The parameter is fixed; endpoints vary across samples.

This is not a statement that 95% of individual travel times fall between 18 and 22. Individual outcomes are usually more variable than sample means.

For the same model, a two-sided 95% t interval excludes exactly the null values rejected by a two-sided 5% t test. Inclusion does not prove a null value true; many nearby values remain compatible.

A worked example, step by step

Interpret a 95% paired interval of (−4,−1) minutes for after−before travel time.

  1. The target is μd, the population mean after-minus-before difference.
  2. The entire interval is negative.
  3. We are 95% confident the mean difference lies between −4 and −1 minutes.
  4. This supports a lower average after time, but causation depends on the study design.
Common mix-up

A fixed interval does not give a frequentist 95% probability that a fixed μ moves into it.

CHECK THE IDEA

Does an interval containing zero prove no difference?

Compare with an explanation

No. It says zero remains compatible at this confidence level.

Now investigate one change Explore →

Predict. Change one thing. Explain.

Generate 100 intervals from a known normal population. Compare the observed capture percentage with the selected confidence level; explain why they need not match exactly.

On narrow screens, swipe or scroll diagrams sideways to read all labels.

First 20 of 100 intervals; vertical line is true μ=201234567891011121314151617181920151719212325Mean time (minutes); interval row numbers at left

96 of 100 intervals capture μ=20 minutes at nominal 95% confidence. A finite run does not guarantee the nominal percentage.

SampleLower (min)Upper (min)Captures μ=20?
118.897523.5126Yes
218.734723.0804Yes
317.842522.6883Yes
418.086121.3421Yes
517.721820.8553Yes
617.063821.604Yes
715.98820.3875Yes
816.119820.3819Yes
918.175622.1905Yes
1015.960520.2365Yes
1117.833521.6735Yes
1217.089721.4468Yes
1318.477422.5961Yes
1419.489423.8458Yes
1518.764523.1272Yes
1617.794621.6868Yes
1718.575623.2333Yes
1817.395321.2206Yes
1916.840620.984Yes
2016.792520.9225Yes
2118.359722.8752Yes
2218.351821.991Yes
2317.216921.6704Yes
2418.050721.9466Yes
2518.422.8014Yes
2618.06422.1571Yes
2718.253822.5797Yes
2819.303123.6066Yes
2915.002619.8986No
3017.726221.7713Yes
3117.044720.0354Yes
3218.238322.8216Yes
3317.797522.6704Yes
3419.729623.9763Yes
3518.622722.3499Yes
3618.467723.4572Yes
3719.657924.2105Yes
3816.945321.5821Yes
3918.512922.5069Yes
4018.02721.6027Yes
4116.984520.7604Yes
4215.532819.3021No
4319.274623.5332Yes
4418.163722.8353Yes
4518.597322.8874Yes
4616.446721.1382Yes
4716.794821.7813Yes
4817.216622.6895Yes
4916.475821.0106Yes
5017.652422.0781Yes
5117.381621.6052Yes
5217.971921.0999Yes
5318.639522.3124Yes
5417.955820.9767Yes
5517.083620.9457Yes
5617.401521.2105Yes
5717.6921.7659Yes
5815.652621.4663Yes
5919.521923.982Yes
6018.900422.5688Yes
6119.613423.6617Yes
6216.349621.8984Yes
6319.26423.1745Yes
6416.48721.2069Yes
6517.117521.4524Yes
6616.386920.7087Yes
6719.022922.608Yes
6817.645821.6084Yes
6917.738821.1978Yes
7017.202221.02Yes
7117.175820.7719Yes
7216.486221.2129Yes
7317.113621.7954Yes
7415.62420.4296Yes
7515.846420.9263Yes
7619.186323.0146Yes
7718.294222.0542Yes
7816.846719.4962No
7918.053322.4398Yes
8019.726924.3421Yes
8117.900822.2198Yes
8217.802521.3578Yes
8317.777122.6215Yes
8416.507420.9143Yes
8517.946522.4297Yes
8618.52823.0863Yes
8716.431920.3736Yes
8819.457722.6564Yes
8917.906922.9669Yes
9017.526121.6817Yes
9118.977222.4774Yes
9217.962723.3519Yes
9320.171823.7204No
9417.627221.1703Yes
9517.679222.0565Yes
9617.633222.3496Yes
9718.71322.6021Yes
9817.076221.4552Yes
9918.625922.379Yes
10017.668821.0252Yes

100 independent simulated samples from a normal population with μ=20 and σ=5 minutes. Each interval estimates σ with its own s and uses t with n−1 df. All 100 intervals enter the table and capture count; the picture shows the first 20. Finite simulation coverage need not equal the confidence level.

Explain what you noticed: Answer the investigation prompt above. State one observation and explain it using the means, standard errors, pairing, graph scales or model assumptions. Identify what the representation cannot tell you.

Apply the idea to a fresh problem Practice →

Show what you understand.

Two original questions are a starting check, not proof of mastery. Explain your choice before revealing the answer.

1. A mean interval describes…

Show answer and reasoning

The population average. Its target is μ.

2. A 95% difference interval (2,5) supports…

Show answer and reasoning

A positive mean difference. All compatible values shown are positive.

Original written challenge

4 points · self-check · not an official AP question

A 90% interval for μ is (40,46) minutes. Assess claims μ=43 and μ=50 and state what 90% means.

This response is not submitted or saved. Copy it before leaving.

Compare with the answer and four-point rubric
  1. 1 point: 43 is inside the interval and compatible.
  2. 1 point: 50 is outside and not compatible with this interval.
  3. 1 point: 90% describes long-run coverage of the interval procedure.
  4. 1 point: Neither conclusion assigns probabilities to the fixed parameter or to individual observations.

Accept equivalent correct methods and explanations. This is a Refresh Kid teaching rubric, not an official AP scoring guideline.

Recall the ideas without notes Review →

Retrieve it before you reveal it.

RECALL 1Does every 95% interval capture μ?

No.

RECALL 2What changes over repeated samples?

The calculated endpoints.

RECALL 3What remains fixed?

The population parameter under the model.

Revisit these tomorrow and a week later. Try a fresh problem and explain why the method applies.

What does confidence say about the population average?

  • Confidence refers to repeated-sample coverage.
  • Interpret the parameter and units.
  • Zero inside a difference interval is compatible with no mean difference.

Remember: A fixed interval does not give a frequentist 95% probability that a fixed μ moves into it.

Conditions: 100 independent simulated samples from a normal population with μ=20 and σ=5 minutes. Each interval estimates σ with its own s and uses t with n−1 df. All 100 intervals enter the table and capture count; the picture shows the first 20. Finite simulation coverage need not equal the confidence level.

Refresh Kid · AP Statistics Unit 4 · Objectives 4.3.A, 4.3.B · Review edition

Framework, scope and review status

Mapped to College Board, AP Statistics CED, Topic 4.3, objectives 4.3.A, 4.3.B. Framework effective Fall 2026, checked September 17, 2026. Unit 4 includes sampling distributions of means, one-sample and paired t inference, and independent two-sample t inference; it is part of the revised five-unit course.

Examples and datasets are synthetic, independently authored teaching material. Mean inference requires a justified design and suitable shape or sample size. Paired analysis uses one sample of differences. Independent two-sample inference uses separate variance estimates and technology-computed Welch degrees of freedom. Extreme skewness and influential observations need attention even in larger samples. This model conservatively withholds inference when those warnings are selected. Conclusions are limited by random sampling and/or assignment as appropriate.

The Organic Chemistry Tutor companion title and destination were located; the full video was not reviewed. Khan Academy’s destination was checked, but its lesson content was not fully readable by the research tool. OpenStax provides optional reference reading. No provider scripts, questions or graphics were copied. Refresh Kid is not affiliated with these providers.

GitHub’s 3D website collection informed optional spatial inspection. Our original paired-data display uses self-hosted Three.js with its MIT license. Two measurement columns are connected within each labeled student lane; horizontal position is before/after, vertical position is time, and depth separates identities rather than representing a numerical variable. Rotation can separate overlapping connectors. Exact values and differences always remain in the 2D table and labeled plot. The broken-matching option is an explicit counterexample, not a legitimate alternative analysis. No autoplay; complete teaching remains available without 3D.

Independent teacher review and observation of students remain pending. Technical checks do not certify statistical accuracy, accessibility or learning effectiveness. This is a review edition.

Released AP Statistics questions and scoring guides are optional. Older exams use the earlier framework, so check alignment before selecting parts. All practice on this page is original, not official AP material.

Learn → Explore → Practice → Review is informed by the IES learning guide. This implementation has not yet been evaluated with learners.

OPTIONAL LIVE SUPPORT

Want to work through this with a tutor?

Bring your question about What does confidence say about the population average? Your explanation and answers remain free to access.

Request a statistics tutor →Ask about this lesson on WhatsAppThe team can confirm teacher availability and next steps.