# Evidence of Absence vs. Absence of Evidence ### Key Idea > Evidence of Absence is different from Absence of evidence. ### Background Consider the prototypical black swan example that Taleb uses. There is a turkey who observes 1000 consecutive days of feeding. These *observations* make up the turkey's *evidence* that the farmer is benevolent and would never do it harm. However, on the 1001st day the turkey is killed for thanksgiving supper. What we can see from this example is that there is indeed *no evidence* of the possibility of a black swan (in this case, death). We can state this concisely as: > There is **no evidence** of a black swan. However, we are likely to confuse the above statement with: > There is **evidence of no** black swans. Notice how strikingly similar the above two statements are (especially from a linguistic perspective). The distance between these two statements, linguistically, is very close. However, the *logical distance* is incredibly vast. Taleb states this problem (and it's underlying cause) clearly here: > Our inferential machinery is not made for a complicated environment in which a statement changes markedly when its wording is slightly modified. Consider in a primitive environment there is no consequential difference between the statements *most killers are wild animals* and *most wild animals are killers*. There is a an error here, but it is almost inconsequential. Our statistical intuitions have not evolved for a habitat in which these subtleties make a big difference. In a medical context there is an acronym, *NED*: > **NED**: No Evidence of Disease. There is no such thing as *END*, Evidence of No Disease. [Naive Empiricism](Naive%20Empiricism.md) [Confirmation Bias](Confirmation%20Bias.md) --- Date: 20220103 Links to: Tags: #review References: * The Black Swan (Chapter 5), Nassim Taleb