Survivorship Bias

The error of judging a group by the members that made it through some selection, while the ones that did not stay invisible.

Visual intuition

3 in 100

before new evidence

You only ever hear from the highlighted 3

100 started; the 3 highlighted are the ones that survived to tell their story. The crowd shows the real odds — 3 in 100 — before the survivors' glowing accounts hide the 97 who did not make it (illustrative counts).

Example

A fund family launches 20 funds, quietly closes the 10 that underperform, and advertises the survivors' return — the visible 10 look brilliant because the failures were deleted from the (illustrative setup).

How It Works

In WWII, analysts mapped the bullet holes on bombers that returned and proposed armouring those spots — until the statistician Abraham Wald pointed out that the returning planes were the survivors: holes on them marked where a bomber could be hit and still fly home, and the fatal spots were on the planes nobody could inspect. That is survivorship : the data has been filtered by making-it-through, so it systematically flatters. It appears wherever failures exit quietly — college-dropout billionaires (the thousands of dropouts who did not get profiled), mutual-fund returns (losing funds get closed and vanish from the books), 'they don't build them like they used to' (the flimsy old buildings are already gone). The antidote is always the same question: who is missing from this ?

Concepts

Sampling Bias

A distorted result caused by looking at data that does not represent the population you care about. More data does not fix the problem if the same kinds of cases are still missing. Before trusting a conclusion, ask who had a chance to appear in the sample and who was left out.

Lessons

A highlighted window showing only part of a larger hidden sample.

The Sample You See Matters

Your conclusion can be wrong when the data you see excludes important missing cases.

Related Facts

Data Tricks

4 min · easy

A plane silhouette covered in bullet-hole dots on the wings and tail, with the engines left unmarked.

The missing planes mattered most

If you reinforce only the bullet holes on returning planes, you may protect the wrong places.

Data Tricks

4 min · medium

A stack of published positive studies on a desk and muted null studies hidden in a file drawer.

Publication bias hides the studies that found nothing

If only exciting results get published, the visible research record can make an effect look cleaner and stronger than it really is.