Survival Bias: What It Is, Causes and Examples
It is easy to see and pay attention only to the successes and not to the failures, which are forgotten. This phenomenon, which derives from selection bias, is called survival bias: a selection error (of objects, of people, of data), precisely based on trusting and taking into account only success stories, Instead, negative cases are ignored.
Survival bias is among the well-studied cognitive distortions in psychology, and examples of it can be found across the board, as success is highly visible in everyday life and people systematically underestimate their chances of achieving it. With this psychology article we will discover what survival bias is, what its causes are and some examples.
What is the survival bias or Neyman fallacy
Survival bias or survival bias is the logical error that is made when focusing on people or things that have passed a certain selection process , ignoring the elements that, on the contrary, have not passed the selection itself. In simple terms, this happens when we select only survivors (those who have outperformed others, be they people, machines, or companies) and come to conclusions based on their attributes, without looking more generally at the entire data set. , including those with similar characteristics that didn't work the same.
The term "survivorship bias" was first used by Allied engineers in World War II. During the conflict, statistician Abraham Wald notoriously took the survival bias in his calculations when he considered how to minimize bomber losses to enemy fire, believing that aircraft that did not return from battle should be examined, without observing the holes in them. bullet in those who did.
In medicine , survival bias is also known as Neyman's Fallacy , which consists of using prevailing cases for case-control studies: prevailing cases are also surviving cases and these may not be representative of all cases. One of the situations that originate this bias is the use of cases detected in screening campaigns, since these cases may have a different evolution than the whole.
Survival bias also describes one of the most common - and important - flaws in data analysis. In fact, survival bias tends to skew the data in only one direction, making the results appear better than they are . A phenomenon ignored in the past by the industry, which can lead to significant distortions in the presentation of data regarding results, which in turn can lead to erroneous investment decisions. In particular, he is accused of overestimating return on assets.
Causes of survival bias
The human brain is programmed through evolution to discover deviations, and that is why we are fascinated by the success stories of those who excel, remembering success information far more than other news.
Survival bias is a predominant cognitive bias, which can be attributed to a fundamental misunderstanding of cause and effect, in particular regarding the concept of correlation with causation. Although correlation and causation may exist, correlation does not imply causation. Causality refers to cases where action A causes the outcome of B, while correlation is simply a relationship, and survival bias causes individuals to believe that the correlation is causal, leading to a misunderstanding. of cause and effect.
Survival bias can lead to overly optimistic beliefs because failures are ignored, but it can also lead to the false belief that successes in a group have some special property, rather than being a mere coincidence.
Examples of survival bias
Once we are familiar with the idea of survival bias, we can start to spot it everywhere: for example, a gym might feature those who have quickly toned up after having been to their facility but of course what they never show they are those who have signed up but have not obtained more than a depleted bank account.
The most famous example of survival prejudice dates back to World War II. At the time, the American military asked mathematician Abraham Wald to study the best way to protect planes from shooting down. The military knew the armor would help, but they couldn't protect the entire plane or they would be too heavy to fly well. Initially, his plan was to examine the aircraft returning from the fight, see where they had been hit the most (the wings, around the tail gun, and the center of the body), and then reinforce those areas. But Wald realized that they had fallen prey to survival bias, because a valuable part of the picture was missing from their analysis.: the planes that had been hit but had not returned. Consequently, the military planned to assemble precisely the wrong parts of the planes: the bullet holes they were seeing indicated the areas where a plane could be hit and keep flying, exactly the areas that did not need reinforcements.