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

Justifying claims

Justifying claims appears in 3 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 Justifying claims is tested

Example 1Easier
A town's library board wants to know whether a majority of adult residents support opening the main library on Sunday mornings. In a random sample of 600 adult residents, 342 (p-hat = 0.57) said they support Sunday morning hours. A 95% confidence interval for the proportion of all adult residents who support Sunday morning hours is (0.530, 0.610). Based on this interval, is there convincing evidence that a majority of all adult residents in the town support Sunday morning hours?
  1. ANo, because a confidence interval cannot be used to evaluate a claim; only a significance test can.
  2. BNo, because the sample proportion of 0.57 is too close to 0.50 to support the claim.
  3. CYes, because every value in the interval is above 0.50, so 0.50 is not a plausible proportion.Correct
  4. DYes, because 95% of the residents in the sample said they support Sunday hours.

Why C is right

The interval checks out: p-hat = 342/600 = 0.57, SE = sqrt(0.57*0.43/600) ≈ 0.0202, and the margin of error is 1.96*0.0202 ≈ 0.040, which gives (0.530, 0.610). A confidence interval gives the plausible values for the population proportion. Every value from 0.530 to 0.610 is above 0.50, so 0.50 (or anything lower) is not plausible. That is convincing evidence that more than half of all adult residents support Sunday morning hours.
Why the other 3 choices miss
A
Misconception that intervals cannot judge claims. A confidence interval can be used to evaluate a claim about a parameter by checking whether the claimed value is plausible, meaning whether it falls inside the interval.
B
Judges the claim by how far p-hat looks from 0.50 instead of using the interval. The interval accounts for sampling variability, and since it lies entirely above 0.50, the difference is convincing.
D
Confuses the 95% confidence level with the proportion of the sample who support the change. The 95% describes the long-run capture rate of the method, and only 57% of the sample said they support it.

Studied alongside

Other concepts from Inference for Categorical Data: Proportions.