Assessing Confounding and Effect Modification of Periodontitis–Systemic Disease Associations
- 44 Downloads
Confounding and effect modification are of increasing importance as periodontal research addresses the putative associations between periodontal disease and systemic diseases. Unfortunately, the importance of confounding and effect modification is not always appreciated and is often overlooked. They may also appear to be similar but they are actually very different. Our goals in controlling them are also different. ‘In epidemiologic analysis one tries to eliminate confounding, but one tries to detect and estimate effect-measure modification’. We also assess effect modification first, since confounding by a variable becomes largely irrelevant if there is also interaction involving that variable.
- Cleophas TJ, Zwinderman AH, Cleophas TF, Cleophas EP. Statistics applied to clinical trials. 3rd ed. New York: Springer; 2006. p. 235–44.Google Scholar
- Parodi S, Bottarelli E. Controlling for confounding in case–control studies. Ann Fac Medic Vet Parma. 2005;25:19–46.Google Scholar
- Rothman KJ, Greenland S. Modern epidemiology. 2nd ed. Philadelphia: Lippincott, Williams & Wilkins; 1998.Google Scholar