selection bias

Terms from Statistics for HCI: Making Sense of Quantitative Data

This is when the way the people who are considered in a study uninitentionally includes some kinds of people more than others and thus nduces a bias in the way resuts are interpretted. This may occur due to sampling bias in the way people are initially selected, or other effects such as self-selection of participants in study, or participants dropping out. Note that this affects both qualitative and quantitative analysis.