This document discusses selection bias, which occurs when there are systematic differences in the characteristics of those selected for a study compared to the overall population from which they were selected. It provides examples of selection bias in case-control and cohort studies. Selection bias can be introduced when the probability of being included in the study depends on both the exposure and outcome of interest. This distorts the association observed in the study sample compared to the true association in the population. Differential participation or loss to follow up based on exposure and outcome status are common causes of selection bias.