Selection Bias Analysis

Selection bias occurs when the study sample differs systematically from the target population.

We quantify it using selection probabilities:

• $S_1^1$ = P(selected | exposed, outcome)
• $S_1^0$ = P(selected | exposed, no outcome)
• $S_0^1$ = P(selected | unexposed, outcome)
• $S_0^0$ = P(selected | unexposed, no outcome)

The bias factor depends on these probabilities.