Overcoming Survivorship Bias
Making Impartial Decisions by Understanding the Psychology Behind it.

Survivorship Bias Definition

Survivorship bias means drawing conclusions from the cases that made it through while the ones that failed have dropped out of view. Investopedia defines it, in investing, as “the tendency to evaluate the performance of existing investments without considering those that have failed, leading to an overestimation of historical performance”. The same trap works anywhere the failures quietly disappear from the sample.

It is closely related to what researchers call selection bias. The Catalogue of Bias, published by the Centre for Evidence-Based Medicine, defines that as a sample that differs “systematically from the population of interest leading to a systematic error in an association or outcome”. A group made only of survivors is a sample like that.

This page covers where the idea is usually illustrated, what is documented about the most famous example, the mental habits that make it easy to fall into, and a few questions that help.

Examples of Survivorship Bias

Most Famous Example of Survivorship Bias

The most famous example is Abraham Wald, a statistician at the Statistical Research Group at Columbia University during the Second World War. The usual telling goes like this: the military looked at the damage on bombers that came back and planned to protect the areas with the most hits, and Wald pointed out the flaw.

The reasoning is sound: the damage you can see is damage a plane survived. Hits in places that brought planes down are under-represented among the planes that return, because those planes are not there to be counted.

What the retelling adds

The most repeated example of survivorship bias has picked up some details of its own along the way.

What is documented:

• Wald’s work survives as “a series of eight memoranda originally published by the Statistical Research Group at Columbia University for the National Defense Research Committee in 1943”, reprinted by the Center for Naval Analyses in 1980.
• The memoranda are mathematics: methods for estimating how vulnerable each part of an aircraft is from the damage on the survivors. In a worked example with made-up figures (“Of 400 planes on a bombing mission, 359 return”), he concludes that “for the observed data of this hypothetical example, the engine area is the most vulnerable”.
• The report names the practical use itself: conclusions from its vulnerability tables “can be used as guides for locating protective armor and can be used to make a prediction of the estimated loss of a future mission”.
• The 1980 reprint says the work “was never published externally”, and that his method “has been employed in the analysis of data from both the Korean and Vietnam Wars”.

What the popular version adds:

• The famous diagram is not his. The aeroplane outline covered in red dots is the work of Cameron Moll, who wrote in 2022 that “sometime around 2005 I hastily plotted fictitious red dots on a poorly-chosen commercial aircraft outline”. He adds that the image seen most often on social media “is from Wikipedia (creator unknown) and is a recreation of my diagram”.
• The tidy ending. The story often ends with the armour being moved in 1943 and crews being saved. The reprinted memoranda say the results can guide where armour goes; they do not report what was actually done with them. Marc Mangel and Francisco Samaniego, who studied the memoranda, wrote in 1984: “We do not know whether it was used during World War II”. They add that in the Vietnam War, analysts used Wald’s techniques on the A-4 aircraft, and that their analysis “led to structural modifications that improved the A-4’s survivability”.

None of this weakens the idea. The logic holds whether or not anyone moved the armour in 1943.

Survivorship Bias in Finance

The clearest everyday case is investment funds. Funds that do badly are often closed or merged into other funds, and in most cases, Investopedia notes, a closed fund’s performance “is not integrated into future reporting”. A list of today’s funds, and their average past returns, therefore leaves out many that did badly, which is why Investopedia describes the result as “an overestimation of historical performance”.

Survivorship Bias in Business

The same shape appears in business stories. The companies that get studied and written about are the ones still standing. If their habits are copied without looking at firms that had the same habits and failed, the habits can look more decisive than they were.

Survivorship Bias in Personal Relationships

Advice from couples married for fifty years is worth hearing, but it comes only from the couples who stayed together. Couples who followed similar advice and split up are not usually asked. The advice may still be good; the sample on its own cannot show that it is.

Psychology of Survivorship Bias

Survivorship bias starts as a problem with the sample, but two well-documented mental habits make it easy to fall into.

The two habits behind it

• The availability heuristic. In a 1974 paper in Science, Amos Tversky and Daniel Kahneman described people judging “the frequency of a class or the plausibility of a particular development” by the “availability of instances or scenarios”: how easily examples come to mind. If successes are the examples that come to mind, the mental sample is skewed before any reasoning starts.
• Confirmation bias. The Catalogue of Bias defines it as “the search for and use of information to support an individual’s ideas, beliefs or hypotheses”. A survivors-only sample supplies plenty of that.

Overcoming Survivorship Bias

The practical version is one question: before drawing a conclusion from a set of examples, ask who is missing from it, and why.

A few follow-ups make that question easier to use:

1. Where did this list come from? A “best funds”, “most successful founders” or “happiest couples” list has already filtered out the failures. Check what the filter was.
2. What happened to the ones that failed? If they had the same habits, strategy or advice, the habit is not what separated them.
3. When and where did the success happen? Conditions such as a rising market or a new industry can do much of the work that later gets credited to a person’s choices.
4. Is there a count of the whole group? A figure that includes the failures, such as all funds launched in a year rather than those still open, gives a truer picture than any list of winners.

Start Making Impartial Informed Decisions

Survivorship bias is easiest to see in other people’s reasoning and hardest to see in your own. The missing cases do not announce themselves; that is the whole problem. Asking “who is not in this picture?” is a small habit, and it applies to a fund brochure, a founder’s life story, a pile of success advice and, as the Wald story shows, to the stories we tell about the idea itself.

Sources

• Abraham Wald, A Method of Estimating Plane Vulnerability Based on Damage of Survivors, reprinted as Center for Naval Analyses Research Contribution 432 (July 1980), from memoranda of 1943.
• Marc Mangel and Francisco J. Samaniego, “Abraham Wald’s Work on Aircraft Survivability: Rejoinder”, Journal of the American Statistical Association 79 (1984).
• Cameron Moll, “Abraham Wald and the airplane diagram with red bullet holes – here’s the origin story” (24 March 2022).
• Investopedia, “Survivorship Bias: Definition and Use in Investing” (updated April 2026).
• Catalogue of Bias (Centre for Evidence-Based Medicine), “Selection bias” and “Confirmation bias”.
• Amos Tversky and Daniel Kahneman, “Judgment under Uncertainty: Heuristics and Biases”, Science 185 (1974).

Checked September 2026. Wald’s 1943 memoranda at Columbia’s Statistical Research Group are documented in the 1980 reprint; the red-dotted aircraft diagram is a modern illustration, drawn around 2005 by its creator’s own account.