Information bias (epidemiology)

"Information bias occurs when there are systematic differences in the way data are gathered from controls and cases. For example, if one set of questions is used to evaluate the exposure in the control subjects, and another set is used for the case subjects, the information about the groups may differ systematically. This could easily lead to distorted inferences. If, in a clinical study, one group is observed more frequently than another, the probability of making an observation will be greater in the one observed more frequently. This kind of bias could occur in a study comparing the effectiveness and safety of two approaches to patient care. If one approach was used for subjects seen in an ambulatory clinic while the other required hospitalization, those in the hospital might be seen more frequently than those in the clinic. Information bias may include observer, interviewer, measurement, recall, or reporting bias."