Common Source Bias

Common source bias is a type of sampling bias that occurs when the dependent variable and the independent variable in a study are both measured from the same group of respondents, so that shared characteristics of that group, rather than any real underlying relationship, can produce a statistical association between the two variables. It has been identified as a particular concern in public administration and organizational research, where combining a performance measure with an explanatory or perceptual measure drawn from the same respondents can generate a false positive association between them. Sources of the bias include the influence of a single researcher's own beliefs and framing on how respondents answer self-report questions, as well as the way a study's method of recruiting or selecting participants, whether by association with the source being studied or by willingness to take part, can itself produce an unrepresentative sample.