Question Wording Bias vs Response Bias
Both terms below come up in the same part of the course, and students mix them up. Here is each one defined on its own, side by side, so you can see where they part company.
Question wording bias
Collecting data and study design
Question wording bias occurs when a confusing or leading survey question pushes responses away from the true value in one direction.
The problem sits in the question itself rather than in who was sampled, which makes it a form of response bias. For example, asking "Do you support wasteful spending on a new stadium?" pulls answers toward no in a way that neutral wording would not. Loaded adjectives and the order the questions come in do the same thing. A separate strand of response bias comes from self-reported answers on topics people are embarrassed to answer honestly. A larger sample just asks the same slanted question more times, so it does not improve the estimate.
Response bias
Collecting data and study design
Response bias occurs when respondents give systematically inaccurate answers, for example due to confusing question wording or pressure to answer a certain way.
Response bias is about the accuracy of the answers people give, not about who is included in the sample. For example, a leading question such as asking whether people support a helpful new policy nudges respondents toward agreement. Sensitive topics can also cause it, since people may understate behaviors they think are frowned upon. Careful, neutral question wording and anonymity help reduce response bias.