weirdfacts

For a sufficiently large random sample, estimate the standard error with p^(1p^)n\sqrt{\frac{\hat p(1-\hat p)}n}. An approximate interval is p̂ ± z*SE, where z* depends on the confidence level. For a 95% interval, z* is approximately 1.96.

The confidence level describes the long-run proportion of intervals constructed by this method that contain the fixed population proportion. It does not say that 95% of individual observations lie within this interval. Greater confidence widens the interval; a larger sample narrows it.

INTERACTIVE MODEL

Try it. Watch it change.

0Population p (teal) · sample estimate (blue)1
p̂ = 0.4 · interval (0.3321, 0.4679)
Large-sample count check met

Each simulated sample uses independent Bernoulli trials. The population p stays fixed while p̂ varies. Before a draw, p is used as the illustrative estimate. Bounds outside [0, 1] are clipped only in the picture.

Explore: Keep the observed proportion fixed. Increase n, then increase the confidence level, and compare interval widths.

Approximate confidence interval
p^  ±  zp^(1p^)n\hat p\;\pm\;z^*\sqrt{\frac{\hat p(1-\hat p)}n}
WORKED EXAMPLE

In a random sample of 400 people, 240 support a proposal. Find an approximate 95% interval.

  1. p̂ = 240400\frac{240}{400} = 0.6.
  2. SE = 0.6(0.4)400\sqrt{\frac{0.6(0.4)}{400}} ≈ 0.024495.
  3. 0.6 ± 1.96SE gives approximately (0.5520, 0.6480).
Assumed knowledge

Sampling distributions and standard normal quantiles.

Learning checkpoints & sourceYOUR LEARNING CHECKPOINT
  • Construct an approximate confidence interval.
  • Interpret coverage and effects of confidence level and sample size.
QCAA Mathematical Methods 2025 v1.3 · p. 30
READY TO TRY IT?

Put the idea to work.

Loading progress…