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

Power

Power appears in 10 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 Power is tested

Example 1Easier
A Type II error occurs when
  1. Athe null hypothesis is rejected when it is actually true
  2. Bthe sample size is too large
  3. Cthe confidence level is set too high
  4. Dthe null hypothesis is not rejected when it is actually falseCorrect

Why D is right

A Type II error (beta) occurs when the test fails to reject a false null hypothesis — the test misses a real effect. This is the complement of power: beta = 1 - power. A Type II error means the data did not provide sufficient evidence to detect a true difference.
Why the other 3 choices miss
A
Incorrect. Rejecting a true H0 is a Type I error (alpha), not a Type II error.
B
Incorrect. A larger sample size actually decreases the probability of a Type II error by increasing power.
C
Incorrect. A high confidence level is related to the confidence interval procedure, not directly to Type II error. While a very high confidence level (very low alpha) does increase the risk of Type II error, setting the confidence level is not itself the error.

Studied alongside

Other concepts from Inference for Categorical Data: Proportions.