Mathematical Methods · Unit 4 · Topic 5

Interval estimates for proportions

Turn a sample proportion into an approximate confidence interval for the population proportion, find and control the margin of error, choose a sample size, and interpret intervals and claims in context.

  • 7 lessons
  • 1 h 44 min of lessons
  • 11 worked examples
  • 11 hours in the syllabus
0 of 7

Start here

From a point estimate to an interval estimate

Lesson 1 of 7 · 12 min

Start the topic

Lessons

7
  1. From a point estimate to an interval estimate (up next)

    See why one sample proportion is almost never exactly right, and why a range of plausible values for p is a more honest and more useful estimate.

  2. Choosing z for a confidence level

    Find the standard normal quantile z that captures the central C% of the distribution, with technology and from the standard values 1.645, 1.96 and 2.576.

  3. Calculating an approximate confidence interval

    Build the approximate confidence interval p^±zp^(1−p^)n\hat{p} \pm z\sqrt{\frac{\hat{p}(1-\hat{p})}{n}} from the normal approximation, and calculate it accurately from survey data.

  4. Margin of error and reading an interval

    Calculate the margin of error, read p̂ and the margin straight from a given interval, and work backwards to the sample size or confidence level behind it.

  5. What 95% confidence really means

    Use repeated sampling to see that intervals vary from sample to sample, that most but not all of them capture p, and how to word the meaning of a confidence level correctly.

  6. Margin of error, confidence and sample size

    See how the margin of error depends on the sample size and the confidence level, and choose the smallest sample that delivers a required margin of error.

  7. Using intervals to judge claims

    Decide whether a claimed proportion is plausible from where it sits relative to a confidence interval, word the conclusion carefully, and model real problems with their assumptions.

  8. Topic quiz

    Ten questions across the topic, from foundation to complex unfamiliar. Your results feed your mastery.

About this topic

A poll of 1500 voters finds that 56% support a new policy. Nobody believes the true figure for every voter in the state is exactly 56%, but it is probably close. How close? This topic answers that question with an interval estimate: a range of plausible values for the population proportion pp, built from one sample and the normal approximation you met in Topic 4.

You calculate approximate confidence intervals p^±zp^(1−p^)n\hat{p} \pm z\sqrt{\frac{\hat{p}(1-\hat{p})}{n}}, find the right zz for a confidence level, and work with the margin of error: how it shrinks as the sample grows and widens as you ask for more confidence, and how to choose a sample size before you collect any data. Most importantly, you learn what "95% confident" really means, why most but not all intervals capture pp, and how to use an interval to judge a claim in a real context, with and without technology.

Before you start

Builds on Continuous random variables and the normal distribution and Sampling and proportions.

  • The sample proportion p^\hat{p} as a random variable with mean pp and standard deviation p(1−p)n\sqrt{\frac{p(1-p)}{n}}, approximately normal for large samples (Topic 4).
  • The standard normal distribution Z∼N(0,1)Z \sim N(0, 1), zz-scores and the inverse normal on a calculator (Topic 3).
  • Binomial probabilities, X∼Bin(n,p)X \sim \mathrm{Bin}(n, p) (Unit 3).
  • Random samples and sources of bias (Topic 4).

What QCAA says you need to know6 dot points

Confidence intervals for proportions

11 hours

Subject matter from the Mathematical Methods General senior syllabus 2025 v1.3 (opens in a new tab), CC BY 4.0 © State of Queensland (QCAA).

The focus areas you can practise on their own. Each one maps to dot points above.

  • Point and interval estimates

    Calculate a sample proportion as a point estimate of p, and explain why a range of plausible values is more useful than a single number.

    Practise
  • Finding z for a confidence level

    Find the standard normal quantile z that leaves the central area C between −z and z, with technology or from the standard values.

    Practise
  • Calculating confidence intervals

    Calculate the approximate confidence interval p̂ ± z√(p̂(1 − p̂)/n) for a population proportion from sample data.

    Practise
  • Margin of error

    Calculate the approximate margin of error, and read the sample proportion and margin of error from a given interval.

    Practise
  • Working back from an interval

    From a given interval, find the sample size or the confidence level that produced it.

    Practise
  • Choosing a sample size

    Find the smallest sample size for a required margin of error, with a prior estimate of p or the cautious p̂ = 0.5, and predict how the margin changes when n changes.

    Practise
  • What the confidence level means

    Interpret a confidence level through repeated sampling, explain why intervals vary and why most but not all contain p, and count intervals with the binomial distribution.

    Practise
  • Judging claims with intervals

    Use whether a claimed value lies inside or outside an interval to judge the claim, and word the conclusion carefully in context.

    Practise
  • Modelling with interval estimates

    Solve unfamiliar problems with intervals, margins and sample sizes, state assumptions such as random sampling, and evaluate the reasonableness of a conclusion.

    Practise

Worked examples11

All 11

Common mistakes

Using the wrong z

For 95% confidence z≈1.96z \approx 1.96, not 1.645 (that is 90%). The central area is CC, so the area to the left of zz is 1+C2\frac{1 + C}{2}: invNorm(0.975), not invNorm(0.95).

Forgetting the square root

The margin of error is zp^(1−p^)nz\sqrt{\frac{\hat{p}(1-\hat{p})}{n}}. Leaving out the root, or taking it of nn only, gives a margin that is far too small or far too big.

Saying there is a 95% probability that p is in this interval

pp is fixed and a calculated interval either contains it or not. The 95% describes the method: about 95% of intervals made this way contain pp.

Rounding a sample size down

A sample size from n=(zE)2p^(1−p^)n = \left(\frac{z}{E}\right)^2\hat{p}(1-\hat{p}) is a minimum. 600.25 means 601 people; 600 would give a margin slightly bigger than required.

Thinking a bigger confidence level gives a better (narrower) interval

More confidence means a bigger zz, so a wider interval. To narrow an interval without losing confidence, increase the sample size.

Thinking doubling n halves the margin

The margin is proportional to 1n\frac{1}{\sqrt{n}}. Halving it needs four times the sample size.

Treating a value inside the interval as proven

A claim inside the interval is plausible, or consistent with the data. It is not confirmed: other values in the interval are also plausible.

Using percentages and proportions together

Use p^=0.56\hat{p} = 0.56, not 56, inside the square root. Convert the final interval back to percentages if the context uses them.

Exam tips

  1. The formula book gives the interval and the margin of error but no zz values. Remember 1.645 (90%), 1.96 (95%) and 2.576 (99%), and know how to get any other zz with invNorm(1+C2)\left(\frac{1+C}{2}\right).

  2. Show the substitution: write p^\hat{p}, nn and zz, then p^±zp^(1−p^)n\hat{p} \pm z\sqrt{\frac{\hat{p}(1-\hat{p})}{n}} with the numbers in. Round only the final endpoints, usually to 3 decimal places (or as asked).

  3. For "interpret the interval", answer in context and name the population: "We are 95% confident that the proportion of all Queensland adults who … is between 0.535 and 0.585."

  4. For "evaluate the claim", say whether the claimed value is inside or outside the interval, then conclude: inside means the claim is plausible (not proven); outside means the data give evidence against it.

  5. When the question asks you to "explain what 95% confidence means", talk about repeated samples: about 95% of intervals made the same way would contain pp.

  6. For a minimum sample size, show the inequality, solve it, and round up. State the p^\hat{p} you used and why (a pilot estimate, or 0.5 to be safe).

  7. Check reasonableness: the interval should be centred on p^\hat{p}, sit inside [0,1][0, 1], and shrink as nn grows. A margin bigger than about 0.1 for a large poll is a sign of an error.

  8. In modelling questions, comment on the assumptions: a random sample, independent responses, and a large enough sample for the normal approximation (np^n\hat{p} and n(1−p^)n(1-\hat{p}) both comfortably large).

Where this shows up

  • Opinion polls in Australian newspapers report a result such as 52% with a margin of error of about 2.5 percentage points: a 95% confidence interval for the proportion of all voters.

  • Public health surveys estimate the proportion of adults who smoke, are vaccinated or meet physical activity guidelines, with an interval that shows how precise the estimate is.

  • Hospitals and regulators compare a hospital's readmission or infection rate with a national benchmark using an interval for the hospital's proportion.

  • Manufacturers estimate the proportion of defective items in a batch from a random sample before deciding whether to ship it.

  • Market researchers choose a sample size in advance so that an estimate of market share is precise enough to act on.

  • Ecologists estimate the proportion of a population with a disease or tag, such as koalas with chlamydia in South East Queensland, from captured animals.

Save your progress with a free account