Abstract :
Are there empirical examples of strong confounding effects? Textbooks usually show examples of weak confounding or use hypothetical examples of strong confounding to illustrate the paradoxical consequences of not separating out the effect of the studied exposure from that of second factor acting as a confounder. HIV infection is a candidate strong confounder of the spuriously high association reported between consumption of poppers, a sexual stimulant, and risk of Kaposi′s sarcoma in the early phase of the AIDS epidemic. To examine this hypothesis, assumptions must be made on the prevalence of HIV infection among cases of Kaposi′s sarcoma and on the prevalence of heavy popper consumption according to HIV infection in cases and controls. Results show that HIV infection may have confounded the poppers-Kaposi′s sarcoma association. However, it cannot be ruled out that HIV did not qualify as a confounder because it was either an intermediate variable or an effect modifier of the association between popper inhalation and Kaposi′s sarcoma. This example provides a basis to discuss the mechanism by which confounding occurs as well as the practical importance of confounding in epidemiologic research.
