Glossary
Bias
Bias occurs when certain responses are systematically favored over others, either intentionally or unintentionally, leading to an underestimation or overestimation of the true value.
Example:
A study on student satisfaction that only surveys students who attend optional club meetings might have a bias towards more engaged students, not representing the entire student body.
Convenience sampling
Convenience sampling is a non-random sampling method where individuals are selected based on their easy accessibility or availability, often resulting in a sample that is not representative of the population.
Example:
A student surveying their friends in the cafeteria about their favorite music genre is using convenience sampling, which likely won't represent the musical tastes of the entire student body.
Nonresponse bias
Nonresponse bias occurs when individuals selected for a sample do not participate or cannot be reached, and their characteristics differ significantly from those who do respond.
Example:
If a survey about healthy eating habits is sent to 1000 people, but only 200 respond, and those 200 are predominantly health-conscious individuals, the results will suffer from nonresponse bias.
Question wording bias
Question wording bias arises when the phrasing of a survey question influences or leads the respondent to a particular answer, rather than eliciting a neutral opinion.
Example:
Asking 'Don't you agree that our school needs more funding for sports?' is an example of question wording bias because it subtly pressures the respondent to agree.
Undercoverage bias
Undercoverage bias happens when a portion of the population has a reduced or zero chance of being included in the sample, making the sample unrepresentative of the overall population.
Example:
A phone survey conducted only using landlines would exhibit undercoverage bias because it excludes individuals who only use cell phones, such as many younger adults.
Voluntary response bias
Voluntary response bias, also known as self-selection bias, occurs when a sample consists entirely of volunteers who choose to participate, often leading to overrepresentation of individuals with strong opinions.
Example:
An online poll asking 'Do you support stricter environmental regulations?' will likely suffer from voluntary response bias, as only those passionate enough to seek out and respond to the poll will participate.