Glossary
Sampling bias
What is sampling bias?
Sampling bias happens when the people or cases in a study differ in relevant ways from the population its findings are meant to describe.
How it happens
A study may rely on volunteers (self-selection), people who are easy to reach (convenience sampling), or only those who stayed in a program (survivorship). Each choice can leave out people whose experiences differ. Henrich and colleagues warned against treating WEIRD samples—Western, Educated, Industrialized, Rich, and Democratic—as representative of humanity.
Example: possible non-response bias
A customer survey gets a 10% response rate. That low rate raises questions, but it does not tell you whether happy, unhappy, or moderately satisfied customers are missing. You need to compare respondents with the people who did not respond.
Why it matters
Before applying a finding, check who was studied and who you want to apply it to. A result from one group may tell you less than you think about another.