AP Statistics / Unit 3: Inference for Categorical Data: Proportions / Topic 3.4
NUM8ERS study notes · Topic 3.4

Justifying a Claim Based on a Confidence Interval for a Population Proportion

A confidence interval gives a range of plausible values. Learn to explain that range, assess claims such as “more than 12\text{more than }\frac12,” and understand what confidence and precision really tell us.

2026–27 curriculum6 worked examples10 practice questionsClaims + visual guides

By the end of this lesson, you should be able to:

  • Interpret a confidence interval using the population and response category.
  • Explain confidence level through repeated random sampling.
  • Decide whether a proposed population proportion is plausible.
  • Use the entire interval to assess a “greater than” or “less than” claim.
  • Explain how confidence level and sample size affect margin of error and width.
  • Write a conclusion that matches the evidence and the sampling design.

Before you start: Know p^=xn\hat{p} =\frac{x}{n} and how a one-proportion interval is constructed. Review Topic 3.3 if you need the formula and condition checks.

First time learning this? Follow the school example, then compare a majority claim with a 60%60\% claim.

Here to revise? Use the interpretation checklist, then try the questions before opening the solutions.

The concept in 60 seconds

A school takes a simple random sample of 500500 students from its 10,00010{,}000 students, without replacement. Of the sampled students, 320320 prefer an earlier lunch. The sample proportion is p^=0.64\hat{p} = 0.64.

After checking the conditions, a one-sample zz-interval gives an approximate 95%95\% confidence interval of (0.5979,0.6821)(0.5979, 0.6821) for pp, the proportion of all students at this school who prefer an earlier lunch.

Visual guide 1: 11 interval can support different claims
Estimate64%64\% in the sample

320320 of 500500 students prefer earlier lunch.

95%95\% interval59.79%–68.21%59.79\%\text{–}68.21\%

A range of plausible values for the whole-school proportion.

Compare the claimAll above 50%50\%; crosses 60%60\%

Supports a majority. Leaves the stronger 60%60\% threshold uncertain.

A claim needs a comparison with the whole interval, not just the center. The school population proportion is unknown.

The school asks two questions:

  • Does a majority prefer earlier lunch? Yes, the interval provides convincing evidence: every value in the interval is above 0.500.50.
  • Do more than 60%60\% prefer it? The interval does not provide convincing evidence for that stronger claim: it includes values just below 0.600.60 as well as above it.

The key habit: Compare the claim with the whole interval. The estimate 0.640.64 alone does not tell you how much uncertainty remains.

Scenarios are fictional teaching examples. The repeated-sampling chart is a documented simulation; the other charts show calculations from stated sample values.

Quick check: does “64%64\% in the sample” prove “more than 60%60\% in the population”?

No. p^\hat{p} is 11 sample result. The 95%95\% interval contains population proportions below 0.600.60, so this interval does not support that population claim convincingly.

Interpret the interval

A confidence interval estimates a population parameter. Here the parameter is a proportion, not an individual student’s response and not the already observed sample proportion.

Sentence pattern: “We are [confidence level] confident that the proportion of [population] who [response category] is between LL and UU.”

School interpretation: “We are 95%95\% confident that the proportion of all students at this school who prefer an earlier lunch is between 0.59790.5979 and 0.68210.6821.”

You can say about 59.79% to 68.21%59.79\%\text{ to }68.21\% instead. Both versions describe the same range on different scales. Include the confidence level, both endpoints, the population and the response category.

Known sample result, unknown population value.
QuantityMeaningSchool example
ppFixed unknown population proportionProportion of all 10,00010{,}000 students who prefer earlier lunch
p^\hat{p}Observed sample proportion320500=0.64\frac{320}{500}= 0.64
LL and UULower and upper interval endpointsAbout 0.59790.5979 and 0.68210.6821 at 95%95\% confidence
Confidence levelLong-run confidence level of the procedure95%95\%
p0p_{0} or kkA proposed value or comparison threshold0.600.60 or 0.500.50, depending on the claim

Keep the sample and population separate

The sample proportion is known: exactly 320500=0.64\frac{320}{500}= 0.64 for these responses. We do not need an interval to learn that value. The interval uses sample information to estimate the unknown proportion in the whole school.

“95%95\% of students prefer earlier lunch” is a different statement and is not supported by this interval. “95%95\% of student responses are between 59.79%59.79\% and 68.21%68.21\%” also makes no sense: each student’s response is a category, such as yes or no.

Write for the actual target population: A sample from this school supports inference about this school when the sampling conditions are met. It does not automatically support a statement about all students in the country.

Quick check: repair “We are 95%95\% confident that p^\hat{p} lies between 0.59790.5979 and 0.68210.6821.”

Replace p^\hat{p} with the population proportion pp, defined in context. p^=0.64\hat{p} = 0.64 is already known from the sample and is the center of this interval.

Explain confidence and coverage

Imagine repeatedly taking random samples of the same size from the same population and constructing an interval by the same method each time. The sample proportion changes, and the interval endpoints change. The population proportion pp stays fixed.

Under suitable conditions, a 95%95\% confidence procedure produces intervals that capture the true pp in about 95%95\% of repeated samples in the long run. Some intervals miss it.

Visual guide 2: changing intervals, fixed population proportion
Repeated confidence intervals and their fixed population targetFirst 40 simulated 95% confidence intervals from independent samples of 200 trials with fixed population proportion 0.60. The vertical dotted line marks 60%. Solid olive lines with dots capture it; dashed brown lines with crosses miss it. 39 capture and 1 miss. 40% 50% 60% 70% 80% Population-proportion scale 1 10 20 30 40 Sample number First 40 simulated 95% intervals · same n = 200; fixed p = 60% Solid + dot: captures p | Dashed + cross: misses p | Shown: 39 capture, 1 miss Repeated confidence intervals and their fixed population targetFirst 40 simulated 95% confidence intervals from independent samples of 200 trials with fixed population proportion 0.60. The vertical dotted line marks 60%. Solid olive lines with dots capture it; dashed brown lines with crosses miss it. 39 capture and 1 miss. 40% 50% 60% 70% 80% Population-proportion scale 1 10 20 30 40 Sample number First 40 intervals Same n = 200; fixed p = 60% Solid + dot: captures p Dashed + cross: misses p Shown: 39 capture, 1 miss

Simulation: 5,0005{,}000 independent binomial samples, n=200n = 200 and

Posted on Google Google
0000003998 : Abdad Alam Shamim Alam profile picture
0000003998 : Abdad Alam Shamim Alam
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
This is the bestest institution I have ever come to and I love it very much.
Posted on Google Google
Aliki S profile picture
Aliki S
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
Posted on Google Google
Ali profile picture
Ali
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
Sly is him
Posted on Google Google
Jitendra Kumar Kumawat profile picture
Jitendra Kumar Kumawat
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
Posted on Google Google
Raahil Hasan profile picture
Raahil Hasan
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
Posted on Google Google
Tina Mudarres profile picture
Tina Mudarres
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
The classes are amazing and my child learnt so much
Posted on Google Google
alisha gadoya profile picture
alisha gadoya
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
I have experienced a lot of good things, it has taught me so many things and from B/Cs I have gone to an A! This is wonderful and Mavish’s class is awesome.
Posted on Google Google
smasher 123 profile picture
smasher 123
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
It’s sensational my kid went. First he only would get C now it’s all A’s really good and recommend
Posted on Google Google
Mosa Al- Samaraie profile picture
Mosa Al- Samaraie
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
AMAZING PRICES GREAT TEACHERS STRAIGHT FORWARD LEARNING STEADY PACE IN TUTORING
Posted on Google Google
Cael Dagnelie profile picture
Cael Dagnelie
Google star 1Google star 2Google star 3Google star 4Google star 5Trustindex verifies that the original source of the review is Google.
I had a great experience learning math with Ms. Mavish. She explains complex topics in a very clear and simple way, which made it easier for me to understand and enjoy the subject. Her patience and dedication really stood out, and she always made sure that everyone in the class was keeping up. I especially appreciated how approachable she was — I never felt afraid to ask questions, and she was always willing to help. Thanks to her teaching, my confidence in math has grown a lot. I’m really thankful for the effort she puts into every lesson!

NUM8ERS is one of finest tutoring institutes in UAE, Located in Al Barsha 1, Dubai. Close to DUBAI AMERICAN ACADEMY (DAA) & AMERICAN SCHOOL OF DUBAI (ASD).