Survivorship bias is drawing conclusions only from the cases that made it through a filter, because the ones that failed are no longer visible. The classic example comes from the Second World War: analysts studied bullet holes on returning bombers and proposed armouring the most damaged areas. The statistician Abraham Wald pointed out that the planes hit in the other places did not come back, so the undamaged areas were the ones that needed armour. The pattern is everywhere. 'They don't build them like they used to' looks only at old buildings still standing. Famous college dropouts who became billionaires are visible; the far larger number of dropouts who did not are not. Investment funds that closed after losing money drop out of the averages, making surviving funds look better. The test is to ask what happened to the cases that are missing, and whether their absence is linked to the outcome you care about. If only winners are counted, any trait shared by winners will look like a cause of winning. After this Concept you can spot a survivor-only sample, name the missing failures, and explain how their absence distorts the conclusion.
Survivorship bias is a thinking error where you judge something only by the cases that survived or succeeded. It is a cognitive bias, a systematic error in judgment, that happens when failures are hi…