Skip to content
AP Statistics · Inference for Categorical Data: Proportions

One proportion z interval

One proportion z interval appears in 4 reviewed AP Statistics questions and sits in Inference for Categorical Data: Proportions. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How One proportion z interval is tested

Example 1Medium
A town council took a random sample of 400 town residents and found that 188 of them support building a new bike lane on Main Street. Using these data, a 95 percent confidence interval for the proportion of all town residents who support the bike lane is (0.421, 0.519). Which of the following is a correct interpretation of this interval?
  1. AAbout 95% of all random samples of 400 residents will have a sample proportion between 0.421 and 0.519.
  2. BWe are 95% confident that the interval from 0.421 to 0.519 captures the true proportion of all residents who support the bike lane.Correct
  3. CBecause 0.47 is below 0.50, the interval gives convincing evidence that fewer than half of all town residents support the bike lane.
  4. DThere is a 0.95 probability that the true proportion of all town residents who support the bike lane is within this particular interval.

Why B is right

The sample proportion is p-hat = 188/400 = 0.47, and the standard error is sqrt(0.47(0.53)/400), about 0.02495. The margin of error is 1.96(0.02495), about 0.0489, so the interval is 0.47 plus or minus 0.0489, or (0.421, 0.519). A confidence interval estimates a population parameter. The correct interpretation says we are 95% confident that this interval captures the true proportion of all residents who support the bike lane. The 95% describes how reliable the method is over many samples. It is not a probability about this one fixed interval.
Why the other 3 choices miss
A
This mixes up the parameter with sample statistics. Sample proportions from other samples center on the true proportion, not on 0.47, so there is no reason 95% of them would land in this particular interval.
C
This ignores the upper half of the interval. The interval runs up to 0.519, so values above 0.50 are still plausible, and the data do not give convincing evidence that fewer than half of residents support the bike lane.
D
This is the probability misinterpretation. After the interval is computed, the true proportion is either in it or not. The 95% describes the long-run capture rate of the method, not a probability for this one interval.

Studied alongside

Other concepts from Inference for Categorical Data: Proportions.