A cohort study is conducted to investigate the association between smoking and lung cancer. Researchers find that participants who smoke heavily are more likely to be lost to follow-up compared to non-smokers. This differential loss to follow-up could lead to which type of bias?

Explanation

Differential loss to follow-up, where the likelihood of participants dropping out of a study is related to both their exposure status and the outcome, is a classic example of selection bias. Selection bias occurs when there are systematic differences between the characteristics of the participants selected for the study and the characteristics of those who are not, or when there are differences in retention that affect the study's internal validity. Information bias (or observation bias) arises from systematic errors in measurement or data collection (e.g., recall bias, interviewer bias). Confounding occurs when an extraneous variable is associated with both the exposure and the outcome, and it distorts the true relationship between them. Recall bias is a type of information bias where cases (those with the outcome) are more likely to remember past exposures than controls.