Statistics for General Practitioners: What is "bias" in research?

Abstract

Researchers often use the term"bias" in order to address concems about reliability and validity of research studies. It does not necessarily carry the imputation of prejudice or other subjective factors such as the researcher's desire for a particular outcome. The aim of this article is to provide some insight into what"bias" is,and to discuss some types of bias encountered in research. Bias can be defined as any efiect at any stage of a research process, or inference thattends to produce rcsuJts that depart s;ntematically from the true values. Hence,for one to appreciate the importance of bias in research, it must be differentiated from the conventional use of the term, which refers to a "partisan" point of view about an issue or "a one-sided inclination of the mind".