
Self-selection bias (also called volunteer bias) refers to the bias that can occur when individuals are allowed to choose whether they want to participate in a research study. Because participants often differ from nonparticipants in ways significant to the research, self-selection can lead to a biased sample and affects the generalizability of your results.
Example: Self-selection bias
Suppose you are surveying high school English students. You ask them to rate the books they read throughout the academic year, but you make participation optional.
Because of that, students who either strongly enjoyed or hated the books are more likely to fill in the survey. Students who didn’t feel strongly about the books are less likely to participate in the survey.
As a result, your sample will comprise mostly those with strong opinions and will not be representative of all students. By allowing students to choose whether to participate, you have allowed self-selection bias to occur.
Self-selection bias refers to the systematic, nonrandom difference in characteristics between individuals who choose to participate in a study and those who don’t.
Studies have shown that individuals who volunteer to respond to surveys tend to be better educated, have higher socioeconomic status, and lead more active lives than those who don’t. Additionally, individuals who are personally interested in a certain topic are more likely to participate in a research study about it.
Self-selection bias occurs when participants differ in some way from nonparticipants. This makes your sample unrepresentative of your population of interest. It also threatens the external validity of your findings—your ability to make generalizations from your sample to the target population.
When a sample contains only participants willing to participate in the survey or experiments, self-selection bias will heavily affect the results.
Non-probability samples, including self-selected or volunteer samples, run the risk of containing too many engaged people, or only containing those with the strongest opinions.
Example: Self-selection bias in polling
News organizations often run polls on social media or their own websites about controversial topics, such as gun control or immigration. After the poll is closed, they report on the results using phrases like “this is what you really think,” “how our viewers felt,” or “what parents think.”
However, these surveys suffer from self-selection bias, because those who feel animated enough by the topic to participate are more likely to do so.
Additionally, it is very challenging to verify that respondents really belong to the intended population. For example, there is no way to easily verify whether respondents to a social media poll about parenting are actually parents.
As a result, these polls tend to overrepresent individuals who have strong opinions, and they are unlikely to accurately reflect public opinion—even with a sample size in the thousands.
Although it’s not always possible to completely eliminate self-selection bias, there are steps you can take to minimize its impact on your findings.
Nikolopoulou, K. (2023, February 03). What Is Self-Selection Bias? | Definition & Example. Scribbr. Retrieved October 30, 2023, from https://www.scribbr.com/research-bias/self-selection-bias/