Confounding occurs when there is a relationship between an exposure, the outcome of interest, and a third factor called a "counfounder" or a "confounding variable". Due to the presence of the confounder, it is not possible to accurately assess the relationship between the exposure and outcome of interest. A counfounder must:
1) be related to the outcome and the exposure;
2) have a different distribution between exposure and non-exposure.
Confounding may be accounted for by randomizing study participants, matching participants by likely confounders (such as age and sex), or controlling the effect of the confounder by stratifying the analysis.
Newhouse, J.P. and M. McClellan. ''Econometrics in Outcomes Research: The Use of Instrumental Variables, Annual Review of Public Health.'' Vol. 19, 1998, pp.17-34.
Gordis, L. 2000. Epidemiology, 2nd ed., Philadelphia, PA: Elsevier Science.
|