What is a confounding variable?

• A. An outside variable related to both exposure and outcome that can distort the observed association.
• B. A variable that is only related to the outcome.
• C. A measurement error in the exposure variable.
• D. A factor that mediates the relationship between exposure and outcome.

Answer: (A)

A confounding variable is a third factor that is related to both the exposure and the outcome, and this relationship can distort or mislead the observed connection between exposure and outcome. If you don’t account for it, you might think the exposure has a stronger, weaker, or even opposite effect than it truly does. For example, age can be linked to how much someone exercises (the exposure) and to the risk of certain diseases (the outcome); if you don’t adjust for age, you could misinterpret the effect of exercise on disease risk. It’s also important to distinguish confounding from other concepts: a variable that is only related to the outcome isn’t a confounder because it doesn’t start or influence the exposure; a mediator lies on the causal path between exposure and outcome, not outside it; and measurement error in the exposure is a different type of bias altogether.