Scribe logoScribeNotes & practice
Sign inStart free
  1. Notes
  2. ›AP Statistics
  3. ›3 Inference for Categorical Data: Proportions
  4. ›3.3 Confidence interval for a proportion

AP Statistics · Unit 3 · Inference for Categorical Data: Proportions

3.3 Confidence interval for a proportion

Calculate and interpret a confidence interval for a proportion, and check the conditions that make the method valid.

  • 4 min read
  • 5 parts
  • 10 questions
  • Draft
Start a Quick 5 on this topic→Jump to the 10 questions
1/5A confidence interval gives a range of plausible values
  1. 1A confidence interval gives a range of plausible values
  2. 2The interval is the estimate plus and minus the margin of error
  3. 3Four steps turn sample data into an interval
  4. 4A confidence level describes the method, not one interval
  5. 5Three conditions must hold before the interval is trustworthy
  6. Check your recall
  7. Practice: 10 questions
1

Part 1 of 5: A confidence interval gives a range of plausible values

A poll reports that 54% of voters support a measure, with a margin of error of 3 percentage points. The poll does not claim the true value is exactly 54%.

Instead it gives a range, from 51% to 57%, built to capture the true population proportion. Such a range is a confidence interval. Its half-width is the margin of error.

A wider range is more likely to capture the truth but tells you less. A narrow range is more precise. Statisticians balance these two goals. News reports often give only the margin of error, but the confidence level matters just as much.

Key terms · tap one for its definition

confidence interval

A confidence interval is an interval calculated from sample data that is built to capture a population parameter with a stated level of confidence.

margin of error

The margin of error is the half-width of a confidence interval, equal to the critical value times the standard error.

Part 1 done

2

Part 2 of 5: The interval is the estimate plus and minus the margin of error

Now build the interval from the sample proportion p^\hat{p}p^​ of a random sample of size nnn. The interval is p^±z∗p^(1−p^)n\hat{p}\pm z^{*}\sqrt{\frac{\hat{p}(1-\hat{p})}{n}}p^​±z∗np^​(1−p^​)​​.

The square-root part is the standard error. It estimates the standard deviation of p^\hat{p}p^​, using p^\hat{p}p^​ in place of the unknown ppp.

The multiplier z∗z^{*}z∗ is the critical value. It comes from the standard normal curve and depends on the confidence level. A larger critical value means a wider interval.

Each piece has a role. The estimate p^\hat{p}p^​ sets the center, and the margin of error sets the width.

Common critical values

Confidence levelz∗z^{*}z∗
90%1.645
95%1.960
99%2.576
Confidence level
90%
z∗z^{*}z∗
1.645
Confidence level
95%
z∗z^{*}z∗
1.960
Confidence level
99%
z∗z^{*}z∗
2.576

Key terms · tap one for its definition

standard error

The standard error of p^\hat{p}p^​ is p^(1−p^)n\sqrt{\frac{\hat{p}(1-\hat{p})}{n}}np^​(1−p^​)​​, an estimate of the standard deviation of the sampling distribution of p^\hat{p}p^​.

critical value

The critical value z∗z^{*}z∗ is the standard normal value that captures the middle C% of the area, where C is the confidence level.

Part 2 done

Quick check

One question on the part you just read

Easy

Identify the expression for a confidence interval for a population proportion.
Show answer and explanation

Answer: B · Worked explanation

The interval is the sample proportion plus and minus the critical value times the standard error. The expression using ppp cannot be calculated because ppp is unknown. One expression drops the square root, and another drops the critical value, so neither gives the correct margin of error.
3

Part 3 of 5: Four steps turn sample data into an interval

Now that the formula is clear, follow the same four steps every time. Because p^\hat{p}p^​ is a proportion, the interval should stay between 0 and 1.

  • Find the sample proportion p^\hat{p}p^​.
  • Calculate the standard error.
  • Multiply by z∗z^{*}z∗ to get the margin of error.
  • Add and subtract the margin of error from p^\hat{p}p^​.

Worked example

A 95% interval for a proportion

In a random sample of 400 adults in a large city, 248 say they use public transit weekly. Construct a 95% confidence interval for the population proportion who do.
  1. 1
    Sample proportion: p^=248400=0.620\hat{p}=\frac{248}{400}=0.620p^​=400248​=0.620.
  2. 2
    Standard error: 0.620(0.380)400=0.000589≈0.0243\sqrt{\frac{0.620(0.380)}{400}}=\sqrt{0.000589}\approx 0.02434000.620(0.380)​​=0.000589​≈0.0243.
  3. 3
    Margin of error: 1.960×0.0243≈0.04761.960\times 0.0243\approx 0.04761.960×0.0243≈0.0476.
  4. 4
    Interval: 0.620±0.04760.620\pm 0.04760.620±0.0476, which gives 0.572 to 0.668.

Answer: The 95% confidence interval is (0.572, 0.668).

Keep extra digits in the middle of the work and round at the end. Report the interval with three decimal places. Then state the result in the context of the problem.

Part 3 done

4

Part 4 of 5: A confidence level describes the method, not one interval

Next, say what the interval means. A good interpretation names the level, the interval and the parameter. For the transit data, we are 95% confident that the interval from 0.572 to 0.668 captures the true proportion. That proportion is for all adults in the city.

The confidence level tells how often the method works. Build an interval from each of many random samples. About 95% of those intervals would capture ppp.

Figure 1. Most intervals cross the dashed line for the true proportion, but a few miss it. The confidence level describes this long-run success rate.

Common mistake

The 95% does not mean there is a 95% chance that ppp lies in one fixed interval. Once calculated, an interval either captures ppp or it does not.

Raising the confidence level widens the interval. A larger sample narrows it.

Key term

confidence level

The confidence level is the percentage of intervals that would capture the parameter in the long run if the method were repeated with random samples.

Part 4 done

Quick check

One question on the part you just read

Easy

Identify the critical value z∗z^{*}z∗ for a 95% confidence interval.
Show answer and explanation

Answer: B · Worked explanation

The critical value for 95% confidence is 1.960. The value 1.645 belongs to 90% confidence, and 2.576 belongs to 99% confidence. Higher confidence levels need larger critical values and give wider intervals. Memorizing these three values saves time when calculating an interval.
5

Part 5 of 5: Three conditions must hold before the interval is trustworthy

The formula assumes the sampling distribution of p^\hat{p}p^​ is approximately normal. Check three conditions to support that, and write them with numbers.

  • Random: the data come from a random sample or a randomized experiment.
  • Independence: nnn is at most 10% of the population size.
  • Large counts: np^≥10n\hat{p}\ge 10np^​≥10 and n(1−p^)≥10n(1-\hat{p})\ge 10n(1−p^​)≥10.

Because ppp is unknown, the large counts check uses p^\hat{p}p^​ here. The counts are the observed numbers of successes and failures. If a condition fails, the stated confidence level may not be accurate.

Worked example

Checking conditions for an interval

In the transit survey, 248 of 400 randomly chosen adults ride weekly. The city has 90,000 adults. Check the conditions.
  1. 1
    Random: the sample is stated to be random.
  2. 2
    Independence: 10% of 90,000 is 9,000, and 400≤9,000400\le 9{,}000400≤9,000.
  3. 3
    Large counts: np^=400(0.620)=248≥10n\hat{p}=400(0.620)=248\ge 10np^​=400(0.620)=248≥10 and n(1−p^)=400(0.380)=152≥10n(1-\hat{p})=400(0.380)=152\ge 10n(1−p^​)=400(0.380)=152≥10.

Answer: All three conditions are met, so the interval method is valid.

Exam tip

Link each condition to a number from the problem. A bare statement that the conditions hold is not enough.

Note read

Check your recall[13 marks]

6 written questions. Answer each one in your head or on paper, then open the mark scheme.

  1. 1.Calculate[3 marks]

    A random sample of 250 people gives p^=0.40\hat{p}=0.40p^​=0.40. Calculate a 95% confidence interval for the population proportion.

    Show mark schemeHide mark scheme

    Model answer

    The standard error is 0.40(0.60)250≈0.0310\sqrt{\frac{0.40(0.60)}{250}}\approx 0.03102500.40(0.60)​​≈0.0310. The margin of error is 1.960×0.0310≈0.06071.960\times 0.0310\approx 0.06071.960×0.0310≈0.0607. The interval is 0.40±0.06070.40\pm 0.06070.40±0.0607, which is (0.339, 0.461).

    • 1 mark for calculating the standard error as about 0.0310
    • 1 mark for multiplying by z∗=1.960z^{*}=1.960z∗=1.960 to get a margin of error of about 0.0607
    • 1 mark for stating the interval as (0.339, 0.461)
  2. 2.Explain[2 marks]

    Explain what is meant by a 95% confidence level.

    Show mark schemeHide mark scheme

    Model answer

    If many random samples were taken and an interval built from each, about 95% of those intervals would capture the population parameter.

    • 1 mark for stating that the method is repeated with many random samples
    • 1 mark for stating that about 95% of the resulting intervals capture the parameter
  3. 3.Describe[3 marks]

    Describe the three conditions to check before calculating a confidence interval for a proportion.

    Show mark schemeHide mark scheme

    Model answer

    The data must come from a random sample. The sample size must be at most 10% of the population. Both np^n\hat{p}np^​ and n(1−p^)n(1-\hat{p})n(1−p^​) must be at least 10.

    • 1 mark for stating the random sample condition
    • 1 mark for stating that the sample is at most 10% of the population
    • 1 mark for stating that np^n\hat{p}np^​ and n(1−p^)n(1-\hat{p})n(1−p^​) are both at least 10
  4. 4.Predict[2 marks]

    Predict how the margin of error changes when the confidence level increases from 95% to 99% for the same sample.

    Show mark schemeHide mark scheme

    Model answer

    It increases. The critical value rises from 1.960 to 2.576, so the interval becomes wider.

    • 1 mark for predicting that the margin of error increases
    • 1 mark for linking this to the larger critical value
  5. 5.Determine[2 marks]

    A random sample of 60 gives p^=0.05\hat{p}=0.05p^​=0.05. Determine whether the large counts condition for an interval is met.

    Show mark schemeHide mark scheme

    Model answer

    It is not met. The number of successes is np^=60(0.05)=3n\hat{p}=60(0.05)=3np^​=60(0.05)=3, which is less than 10.

    • 1 mark for calculating np^=3n\hat{p}=3np^​=3
    • 1 mark for concluding that the condition fails because 3 is less than 10
  6. 6.Identify[1 mark]

    Identify the critical value z∗z^{*}z∗ for a 90% confidence interval.

    Show mark schemeHide mark scheme

    Model answer

    The critical value is 1.645.

    • 1 mark for identifying 1.645

Practice this topic

10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)

0 right0 of 10 answered

Includes the 2 quick checks in the note above.

3.

Easy·Identify[1 mark]

Identify the margin of error of a confidence interval.
Show answer and explanation

Answer: C · Worked explanation

The margin of error is the critical value times the standard error, which is half the width of the interval. The distance between p^\hat{p}p^​ and ppp is the actual error in one sample, and it is unknown. It is not a probability, and it is not the population standard deviation.
4.

Medium·Determine[1 mark]

A random sample of 250 shows p^=0.40\hat{p}=0.40p^​=0.40. Determine the margin of error for a 95% confidence interval.
Show answer and explanation

Answer: C · Worked explanation

The standard error is 0.40(0.60)250≈0.031\sqrt{\frac{0.40(0.60)}{250}}\approx 0.0312500.40(0.60)​​≈0.031, and 1.960×0.031≈0.0611.960\times 0.031\approx 0.0611.960×0.031≈0.061. The value 0.031 is the standard error without the critical value. The value 0.051 uses z∗=1.645z^{*}=1.645z∗=1.645 for 90% confidence, and 0.080 uses z∗=2.576z^{*}=2.576z∗=2.576 for 99% confidence. Match the critical value to the stated level.
5.

Medium·Identify[1 mark]

A 95% confidence interval for the proportion of students who walk to school is (0.41, 0.53). Identify the correct interpretation.
Show answer and explanation

Answer: A · Worked explanation

A correct interpretation names the confidence level, the interval and the population parameter. The interval is about the proportion of all students, not about individual students. It does not give the chance that a future sample proportion lands there, and it does not describe how all sample proportions are spread.
6.

Medium·Predict[1 mark]

The same data are used to build a 90% interval instead of a 95% interval. Predict how the interval changes.
Show answer and explanation

Answer: D · Worked explanation

The critical value falls from 1.960 to 1.645, so the margin of error shrinks and the interval is narrower. The standard error stays the same because nnn and p^\hat{p}p^​ do not change. The interval is not unchanged, since the critical value depends on the confidence level.
7.

Medium·Identify[1 mark]

Each sample below is random and much smaller than 10% of its population. Identify the sample that meets the large counts condition for an interval.
Show answer and explanation

Answer: C · Worked explanation

With n=50n=50n=50 and p^=0.50\hat{p}=0.50p^​=0.50, there are 25 successes and 25 failures, both at least 10. The sample of 40 has 8 successes, the sample of 100 has 6 successes, and the sample of 300 has 9 failures. Each of these has one count below 10, so it fails.
8.

Hard·Determine[2 marks]

A random sample of 500 gives p^=0.30\hat{p}=0.30p^​=0.30. Determine the 90% confidence interval for the population proportion.
Show answer and explanation

Answer: B · Worked explanation

The standard error is 0.30(0.70)500≈0.0205\sqrt{\frac{0.30(0.70)}{500}}\approx 0.02055000.30(0.70)​​≈0.0205. The margin of error is 1.645×0.0205≈0.03371.645\times 0.0205\approx 0.03371.645×0.0205≈0.0337, giving 0.266 to 0.334. The interval 0.260 to 0.340 uses z∗=1.960z^{*}=1.960z∗=1.960, and 0.247 to 0.353 uses z∗=2.576z^{*}=2.576z∗=2.576. The interval 0.280 to 0.320 uses the standard error alone.
9.

Hard·Determine[2 marks]

Two random samples of the same size from one population give 95% intervals of 0.48 to 0.56 and 0.52 to 0.60. Determine which statement is correct.
Show answer and explanation

Answer: D · Worked explanation

Different random samples give different sample proportions, so their intervals differ even when the method works as intended. Overlap does not prove where the true proportion lies. Both intervals use the same 95% level, and the level describes the method rather than where an interval sits.
10.

Hard·Determine[2 marks]

A random sample gives a 95% interval for a proportion. Determine how the sample size must change to cut the margin of error in half, with the same confidence level and p^\hat{p}p^​ unchanged.
Show answer and explanation

Answer: B · Worked explanation

The margin of error is proportional to 1n\frac{1}{\sqrt{n}}n​1​. Halving it needs n\sqrt{n}n​ to double, so nnn must be multiplied by 4. Doubling nnn only divides the margin of error by 2≈1.41\sqrt{2}\approx 1.412​≈1.41. Increasing nnn by 50% gives a smaller improvement still.

Keep going

Next topic3.4 Claims from a proportion intervalPrevious topic3.2 Sample proportions

More in Unit 3 · Inference for Categorical Data: Proportions

  1. 3.1EstimatorsNotes · 10 questions
  2. 3.2Sample proportionsNotes · 9 questions
  3. 3.3Confidence interval for a proportionNotes · 10 questions
  4. 3.4Claims from a proportion intervalNotes · 10 questions
  5. 3.5Setting up a test for a proportionNotes · 10 questions
  6. 3.6p-valuesNotes · 10 questions
  7. 3.7Carrying out a test for a proportionNotes · 10 questions
  8. 3.8Errors in testsNotes · 10 questions
  9. 3.9Differences in sample proportionsNotes · 10 questions

All AP Statistics topics →

Draft: written by Scribe and checked automatically, not yet by a subject reviewer.

Practice questions are original, written by Scribe and checked automatically for correctness.

Topic codes follow the official numbering. Not endorsed by College Board or any exam board.

On this page

0/5 read

  1. 1A confidence interval gives a range of plausible values
  2. 2The interval is the estimate plus and minus the margin of error
  3. 3Four steps turn sample data into an interval
  4. 4A confidence level describes the method, not one interval
  5. 5Three conditions must hold before the interval is trustworthy
  6. Check your recall
  7. Practice: 10 questions
All coursesScribeHow it worksPricingPrivacyTerms

Notes and questions are written by Scribe in our own words. Topic codes follow the official course numbering so you can find your place. Not produced or endorsed by the IB, College Board, AQA, OCR, Pearson Edexcel or any exam board.

© 2026 Scribe