Skip to content
AP Statistics · Exploring One-Variable Data and Collecting Data

Undercoverage bias

Undercoverage bias appears in 4 reviewed AP Statistics questions and sits in Exploring One-Variable Data and Collecting Data. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Undercoverage bias is tested

Example 1Easier
A polling firm is conducting a telephone survey about political preferences. They randomly dial landline phone numbers from a directory. Which of the following groups is most likely to be underrepresented in this sample?
  1. ARetired adults who are frequently at home
  2. BPeople who live in urban areas with widespread phone coverage
  3. CPeople who enjoy discussing politics
  4. DYounger adults who rely only on cell phones, not landlinesCorrect

Why D is right

Using only landline directories systematically excludes people who only use cell phones. Younger adults are much less likely to have landline phones, creating undercoverage bias. This group's political preferences may differ from those of landline users, skewing the results.
Why the other 3 choices miss
A
Incorrect because retired adults are more likely to have landlines and be available to answer, making them overrepresented, not underrepresented.
B
Incorrect because urban areas have extensive landline infrastructure, so urban residents would not be systematically underrepresented.
C
Incorrect because people who enjoy discussing politics may be more willing to respond regardless of phone type.

Studied alongside

Other concepts from Exploring One-Variable Data and Collecting Data.