Survivorship Bias
Judging from the winners you can see, while the losers who'd change the story are invisible.
Also known as: Silent-evidence bias
intermediate Attributed to Abraham Wald · Statistics; popularised via Abraham Wald's WWII work
Survivorship bias is drawing conclusions from a sample that has been filtered to include only "survivors," while the failures — which dropped out and left no trace — are silently excluded. Because the losers are invisible, the survivors look more representative than they are.
What it is
When you study only what made it through, you learn what the survivors have in common — but you can't tell whether the failures had those same traits too. If "drop out of college" describes both billionaire founders and a mountain of forgotten failures, then dropping out isn't the cause of success; it's just visible in the winners because the losers are gone.
The classic case: in WWII, analysts examined returning planes to decide where to add armour, planning to reinforce the areas with the most bullet holes. Abraham Wald pointed out the flaw — those were the planes that survived hits there. The armour belonged where the survivors had no holes, because planes hit in those spots never came back to be studied.
The bias hides in success stories, backtested strategies, and "habits of the highly successful" — anywhere the failures have quietly disappeared from view.
Worked example
A book studies ten wildly successful companies and finds they all "took bold risks." The conclusion — take bold risks — ignores every company that took equally bold risks and went bankrupt, none of which made the book. Since the failures are invisible, boldness looks like a formula for success when it may be a formula for high variance. The sample was filtered by survival before the lesson was drawn.
How to counter it
As a bias, the danger is confident conclusions from a filtered sample. The antidote is to ask, every time: what's missing from this sample? Who or what failed and didn't make it into view? Seek out the failures deliberately, because they carry exactly the information the survivors can't.
How to apply it
- Ask "who or what isn't in this sample because they failed?"
- Before copying the winners' habits, check whether the losers had them too.
- Distrust success formulas drawn only from success stories.
- Actively hunt for the silent evidence — the planes that didn't return.
Related entries
Sources & further reading
The Black Swan
by Nassim Nicholas Taleb · book
Taleb writes extensively on silent evidence and the graveyard of failures we never see.
Affiliate link — we may earn a commission, at no extra cost to you.