Description

A bias that has been considered for the duration of the existence of social science, response bias describes a multitude of possible ways in which subjects of a survey or experiment could represent themselves inaccurately. While it was once thought that a large enough sample could make this problem negligible, it is now understood that if the bias is systematic, it will have an effect. One form of this bias is acquiescence bias, or the tendency to say ‘yes’. Another is demand characteristics, which occurs when subjects attempt to make the experiment have a certain result. A third form is extreme responding, which is the tendency to choose the strongest option in surveys. Finally, there is social desirability bias; subjects don’t want to admit their misdeeds and flaws to experimenters. It is important to understand and minimize these biases to conduct accurate social science.

Example

For example, if researches are conducting a survey about spanking children, and they conduct this study through in person interviews, they would likely obtain an inaccurate sample. Because of social desirability bias, people are less likely to want to report spanking. To neutralize response bias, the researchers could use a less personal method of surveying.

Further Reading

The Decision Lab

The Decision Lab is a think tank focused on creating positive impact in the public and private sectors by applying behavioral science.

Get In Touch