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

Survey wording

Survey wording appears in 3 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 Survey wording is tested

Example 1Easier
A comparison of two survey questions illustrates response bias: Version A: 'Do you support or oppose stricter regulations on industrial pollution?' Version B: 'Do you support job-killing regulations that burden businesses with excessive pollution compliance costs?' Which of the following best describes the expected effect of Version B compared to Version A?
  1. ABoth versions will produce the same results because they ask about the same topic
  2. BVersion B will produce lower support because of its loaded wordingCorrect
  3. CVersion B will produce more nonresponse because it is a longer question
  4. DVersion B will produce higher support for regulations because it mentions jobs

Why B is right

Version B uses negatively loaded language ('job-killing,' 'burden,' 'excessive') that frames regulations in an unfavorable light. This biased wording primes respondents to view regulations negatively, reducing reported support compared to the neutral Version A. This is a textbook example of how question wording can create response bias.
Why the other 3 choices miss
A
Incorrect. Decades of survey research demonstrate that question wording significantly affects responses, even when the underlying topic is the same. Loaded language consistently shifts opinions.
C
Incorrect. While slightly longer questions can sometimes increase nonresponse, the primary effect of Version B is to shift the content of responses through biased wording, not to change response rates.
D
Incorrect. The mention of jobs is framed negatively ('job-killing'), which would decrease rather than increase support for regulations.

Studied alongside

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