The Survivorship Bias is harmful due to how commonly it occurs and how profoundly the bias can influence our choices. Commonly, this bias is linked to financial decision-making, entrepreneurship, gambling, and medical research. When making decisions in these sectors, we must make sure to consider both the successes and the failures. If not, survivorship bias can profoundly impact our perceptions and judgments. Without having all the data needed to make rational decisions, individuals will not be able to make the best possible choice for themselves. Here are some important ways the bias can sway your judgments and decisions:

Overly optimistic expectations

Survivorship bias often causes us to judge our own chances of success based on visible successes. As mentioned above, this is overwhelmingly apparent in the world of businesses, where a few successful individuals overshadow the failures of the majority, making individuals overly optimistic about their own prospects—and subsequently ill-prepared for challenges. This is not just a problem for aspiring entrepreneurs. Actors, musicians, artists, athletes, and even social media influencers can be misled by the success of those who have “made it,” developing unrealistic or misguided career strategies with potential financial (and emotional) consequences.

Investors frequently face similar pitfalls due to the survivorship bias. An investor might judge the success of a startup based on how closely it resembles successful companies rather than considering the countless failed startups that share similar traits. Similarly, they could misjudge the past performance of a mutual fund by only considering successful investments, overlooking those that failed so miserably that they no longer exist at all. This inflates the average return of funds and can create a sense of false optimism for investors, increasing the chance that they’ll make the wrong investment decision—known in the world of finance as survivorship bias risk.¹⁴

Underestimating risk

This bias can also make us vulnerable to reckless ideas, encouraging us to emulate the risky behaviors of successful people—some of whom survived against all odds. For instance, we might underestimate the risk associated with extreme sports by focusing on successful athletes, overlooking the many individuals who were injured or killed doing the same thing. Consider that only around 60% of people attempting to climb Mount Everest successfully reach the summit, and 1% tragically die in the process.¹⁵ Despite these numbers, summit success stories can give us an inaccurate perception of the risks involved in mirroring the behavior of successful survivors.

In a similar vein, survivorship bias is why scientists recommend against taking health advice from the world’s oldest people.¹⁶ Centenarians, or people who live to 100 years old, are often asked to spill their longevity secrets. While many centenarians do have a lot of great advice—exercise frequently, eat a healthy diet, get sufficient sleep, etc.—some report less healthy habits like drinking a glass of hard liquor daily or eating bacon for breakfast every morning. A few centenarians are even active smokers! This doesn’t mean those habits contribute to longevity. Rather, it suggests that these lucky individuals have survived despite their habits, possibly due to genetic factors. These examples show just how risky it is to blindly heed the advice of visible survivors while overlooking all the people who behaved similarly but did not succeed.

Overlooking valuable lessons in failure

Losing sight of the whole picture exposes us to unrealistic expectations and risky endeavors and blinds us to potential learning opportunities. There are valuable lessons to be learned in observing the failures of others. Unfortunately, when we assume a successful subgroup represents the entire group, we forget to evaluate the failures of all those who did not make it. Following the strategies of successful entrepreneurs means missing critical insights from failed startups. Similarly, focusing on the success stories of people who followed certain fad diets means missing out on relevant reasons other people gave up on the diet, such as potential health risks or unrealistic limitations that made it unsustainable for more people. In short, studying failure alongside successes provides a more balanced perspective that helps us make better decisions for ourselves.

Survivorship bias is everywhere we look, as it is a common bias that affects how we interpret data and information when making decisions. Survivorship bias also affects high-level decision-making, which then results in systemic challenges across multiple disciplines. 

Historical Narratives

It is important to consider how the survivorship bias can impact how we look at history, and thus, how we come to understand our world. Depending on the school, the way information is presented and the materials being used can create bias. The focus on certain groups and their successes across history can diminish the stories and struggles of others. Avoiding the discussions of exploitation can give us an inaccurate picture of how several countries came to be and why certain groups seem to have an unfair advantage in the modern age. Looking at the bigger picture, trapping ourselves in the survivorship bias informs our views on systemic racism as well as other inequalities. In order to drive social progress it is important to look at both the triumphs and the great injustices of history.

Epidemiology 

Survivorship Bias has been found in instances of disease diagnoses, specifically concerning survival rates post-diagnosis. For example, patients with the best prognosis are often those with the lowest risk due to their age, previous health history, and fitness level. The more patients display these positive precursors, the better their survival rates. Because patients with a worse health history, do not always survive, their fatality is not included in survival rate calculations. Meaning, patients are disproportionately represented by healthier individuals who have positive outcomes. What should also be taken into account are individuals who die shortly after being diagnosed or those who die prior to being officially diagnosed. By not being included in survival rate calculations, survival outcome is inflated.⁴

During the COVID-19 pandemic, a huge point of question was the survival rate. Many epidemiologists and doctors warn that publicized calculations do not provide a full picture. Patients who die without being tested for COVID-19 cannot be considered part of the virus’ death count, potentially skewing survival rates. In many countries globally, nations and their healthcare systems had issues keeping up with testing, resulting in potential survivorship bias when looking at data generated from the disease.⁵

Survivorship bias occurs because we have a tendency to focus on successful outcomes while overlooking examples of failure, but why do we do this? Why don’t we weigh a group’s successes and failures equally when judging their behavior? Here are a few behavioral science insights that might explain this tendency:

Successes are more visible than failures

One key reason for survivorship bias is that successes are more readily accessible than failures. Try to think of some examples of successful startups. Chances are, prominent companies like Airbnb, Facebook, Uber, and Netflix come to mind quite easily. Now, try to recall some failed startups. Not so easy, is it? Success stories are glorified by the media and amplified by their existing presence in our world, while failures tend to fade into the background.

Not only that, but because we can easily recall these success stories, we tend to give them more weight when evaluating probability. This phenomenon, called the availability heuristic, explains how we prioritize information that comes to mind quickly when deciding the likelihood of something happening in the future. Because it’s easier to recall the successes of a subgroup than the failures of the majority, we tend to think these successes are more likely to occur than they really are.

However, it’s not always the case that we simply overlook examples of failure. Sometimes data on non-survivors is simply not available at all. For example, individuals are often excluded from epidemiological studies because they either died or developed the disease in question before the study started, causing researchers to draw incorrect conclusions about the relationship between particular behaviors or medical interventions and health outcomes. One study on alcohol consumption and mortality among seniors found that people who drank a lot of wine had lower mortality rates than those who drank less.¹⁷ At first glance, these results make it seem that drinking wine somehow helps people live longer. However, it is possible that some of the high-consumption wine drinkers had died before entering the study, so the study only included those who were healthy enough to survive and continue their wine-drinking ways. With this in mind, the results may have had more to do with the overall health status of the participants than the wine itself.

We see what we want to see

Confirmation bias, or the tendency to give more weight to information that confirms our existing beliefs, can also contribute to the survivorship bias. Say you believe that you’re going to make it big as an entrepreneur. You’re more likely to pay attention to information that supports this idea (stories of successful business people) than information that discredits it (stories about startups that failed). Similarly, when people think that a certain diet is the best way to eat, they’ll often focus on long-living individuals who thrived on the diet while ignoring those who did not do well on it. Confirmation bias and survivorship bias create a cycle of reinforcement where we believe something is true, we look for information that confirms it, and then use this information to make broader generalizations about expected outcomes.

We assume correlation equals causation

Survivorship bias can also be attributed to a fundamental misunderstanding of cause and effect, specifically concerning the concept of correlations versus causation.⁶ Though correlation and causation may exist in unison, correlation does not imply causation.⁷ 

Simply because individuals observe a pattern from a dataset, such as the above-mentioned example of successful entrepreneurs and dropping out of school, does not mean that all successful entrepreneurs drop out of school or that all those who drop out of school will be successful. Causation refers to cases where action A causes B’s outcome, whereas correlation is simply a relationship. The coincidence that many entrepreneurs dropped out of university is a correlation, as the event of dropping out of school did not necessarily cause their success. The Survivorship Bias, however, causes individuals to believe that the correlation is causation.⁷ 

Being aware of survivorship bias and understanding how it can impact your judgment and decision-making is critical to ensure you're practicing critical thinking and making the best possible decisions for yourself. 

Both in our individual lives and on a systemic level, an awareness of survivorship bias can help us avoid making flawed conclusions based on incomplete data. This is of particular importance in research, as the bias can cause researchers to draw conclusions that are only applicable to a specific subgroup of “survivors,” but not to the group as a whole. For example, a UK study on mental health during the COVID-19 pandemic found that those who experienced symptoms of anxiety and depression were less likely to complete follow-up surveys.¹⁸ As a result, these respondents were excluded from the final analysis, making it appear as if anxiety and depression rates had dropped following an initial spike early in the pandemic. 

This study perfectly highlights the hazards of overlooking this form of survivorship bias in research. Generalizing a group of survivors as representative of the entire group could lead to inaccurate conclusions, like that mental health is improving when it is not. This is especially problematic when this research influences decisions about resource allocation. To draw conclusions about a group, we have to look equally at both survivors and nonsurvivors, seeing the whole distribution of outcomes rather than just the successes.

As we’ve explored, survivorship bias can impact individuals across several domains; thus, awareness can ensure better product decisions, financial investments, or scientific conclusions. Developing biases is an unavoidable human trait, but taking our time to challenge them is necessary to ensure that we make the best decision we possibly can. 

Once they are aware of survivorship bias, individuals can practice avoiding it in several ways. 

Ask yourself what you don’t see

When making a decision, begin by considering what’s missing. What data didn’t “survive,” from an event or dataset you are using? By asking questions and taking the time to research these missing data points, you can develop a better understanding before your decision-making moment. Being fully informed and taking the time to pause, reflect, and research will help ensure the consideration of survivorship bias in your decision-making.⁶

Study the failures

When you’re sure you have all the information you need to make a decision, take a good look at the failures. Study examples that started along the same path but didn’t work out. For example, when you hear about a tech startup that grew into a wildly successful company, seek out tech startups that launched with a similar idea but failed to make it, then try to find out where they went wrong. When you hear about someone who lost a lot of weight on a trendy diet, look for others who tried the same diet and didn’t see success, then find out what factors contributed to their outcome.

Understanding why something failed can often be more valuable than making assumptions about why something else was successful. Failures give us concrete evidence (startup A failed because they ran out of money), while successes can be attributed to any number of causes (maybe startup B was successful out of sheer luck and not because the founder wore the same shirt every day). The more you understand the failures of the invisible majority, the better you’ll be able to avoid common pitfalls.

Vet your data sources 

Another method to prevent survivorship bias, specifically in your work and research, is to be selective of the data sources used. By ensuring data sources are crafted to promote accuracy and do not omit critical observations that would change analysis results or decision-making, individuals can reduce the risk of survivorship bias.¹

One of the most famous illustrations of survivorship bias comes to us from Abraham Wald, a famous statistician known for studying World War II aircraft as part of his work at Columbia University. When Wald’s research group attempted to determine how war bomber planes could be better protected, the group's initial approach was to assess which aircraft parts had incurred the most damage. After identifying areas that were in the worst condition, they would then reinforce the aircraft with more protection in those locations. However, Abraham Wald noted that the aircraft that were most heavily damaged were the ones that had not returned to American bases—in other words, the ones that did not survive. Those same airplanes would provide the most relevant information regarding which parts of the aircraft would need to be reinforced.⁸

Had this research group been unable to identify this critical fact, the aircraft reinforcements they would have suggested would have ignored entirely a subset of planes that arguably had the most valuable data points regarding the project. The research study results provided an example of how Abraham Wald and his research group at Columbia overcame survivorship bias, saving hundreds of lives.⁸ 

“What you should do is reinforce the area around the motors and the cockpit. You should remember that the worst-hit planes never come back. All the data we have come from planes that make it to the bases. You don’t see that the spots with no damage are the worst places to be hit because these planes never come back.”

— Abraham Wald, Hungarian mathematician and pioneer in decision theory.

A significant portion of marketing campaigns involve testimonials – data that the consumer values highly. We often want to know if a product will work, so we may turn to the “clinical trials” and independently funded studies presented in advertisement campaigns. However, there may be more behind the numbers: a flashy “95% of people saw improvement!” doesn’t always tell the full story. When we aren’t made aware of the full parameters of a study, it is easy to get a biased perspective. It’s always a good idea to double check the rigor of a study. For example, what was the sample size? Did people drop out of the study? How long did they use the product for? All of these questions are important in order to determine its validity. When we take these points into account we are actively working against the survivorship bias.

Incorporating rich data sets and employing rigorous evaluation methods may mitigate the effects of survivorship bias on AI software. However, artificial intelligence is an ever-growing field and widespread use can cause multiple companies to pitch the next big advancement. While technological progress is exciting, pumping out software too quickly could lead to oversight. 

Specifically, it is important not to overestimate the success rates of artificial intelligence, especially the most recent technology. We don’t always consider the multiple failures that allow us to achieve refined systems later on. Underestimating the  limitations of AI can cause us to fall victim to the survivorship bias. This leads to using AI in a way that misinforms our decision-making or researching. 

Survivorship bias also impacts financial systems. A typical example of survivorship bias can be seen in mutual fund performance. Specifically, survivorship bias describes the tendency for companies or mutual funds to be excluded from performance analysis studies. The results from these studies assessing financial markets are then skewed in a more positive light, as only companies that were successful and “survived,” were included in the study.⁹

Survivorship bias can be examined more specifically in the case of mutual funds. A mutual fund is a financial vehicle that pools money collected from investors and is managed by a professional fund manager. Fund managers take that money and invest in things like stocks, bonds, and other assets.¹⁰ When looking at mutual funds’ investments, it only includes those that are currently successful. Funds that were previously opened and lost money would be either closed or merged with other funds, which hides past poor performances.

Survivorship bias occurs when analysts calculate performance results of groups of investments, such as mutual funds, using only the surviving data at the end of the period, and exclude merged funds or defunct funds from companies that no longer exist at the end of a study. For example, in a financial universe where 1,000 funds exist, imagine that 10% of these funds stop existing by year's-end due to poor performance. If an analyst is conducting a performance review of these funds but only begins the study at the end of the year, the analyst would fall prey to survivorship bias and omit the failed funds from their final results. By not including funds that failed, the performance data would indicate a more favorable final result for the theoretical fund universe.⁹

In 1996, researchers Elton, Gruber, and Blake analyzed the relationship between fund sizes and survivorship bias. They found that survivorship bias was more significant in the small-fund sector than in more significant mutual funds. Smaller funds have a higher probability of folding than larger, more established funds, which is why they attributed this to be true for the small-fund sector.¹² The researchers estimated the size of survivorship bias across the United States mutual fund industry as 0.9% annum. Additionally, they defined and measured survivorship bias as the following: 

"Bias is defined as average α for surviving funds minus average α for all funds" (Where α is the risk-adjusted return over the S&P 500. This is the standard measure of mutual fund out-performance).¹²

Another example of survivorship bias can be seen in the medical field and medical research. In 2010 at the Harvard Medical School and Beth Israel Deaconess Medical Center (BIDMC), a study was conducted in hopes of improving patient survival following trauma. A major concern when treating trauma is irregular bleeding. If the patient's blood does not clot properly, the risk of bleeding to death is high.¹³

The Harvard study investigated whether giving trauma patients additional proteins, which naturally occur in our bodies, would encourage blood clotting and improve survival rates. The study targeted patients who had received 4-8 blood transfusions within 12 hours of their initial injury. The trial hoped to recruit 1502 patients, but only recruited 573, and thus was later abandoned.¹³

This study’s failure was due to survivorship bias, as the trial only included patients who had survived their initial injury, and who had then received care in the ER before being transferred to the ICU for 4-8 blood transfusions. Patients who died from their initial injury were not included in the study, making it challenging to find suitable patients for the trial.¹³

What it is

Survivorship bias is a type of sample selection bias that occurs when an individual mistakes a visible successful subgroup as the entire group. In other words, survivorship bias occurs when an individual only considers the surviving observation without considering those data points that didn’t “survive” in the event. 

Why survivorship bias happens

Survivorship bias occurs in many disciplines, professions, and fields of research. Survivorship bias can be attributed to the fundamental misunderstanding of cause and effect and a skewed perception of correlation versus causation. 

Example 1 - Financial systems

The Survivorship Bias occurs in our financial systems, when individuals calculate performance results of groups of investments, such as mutual funds, using only the surviving data at the end of the period, excluding those funds or companies that no longer exist. Typically, mutual funds no longer exist due to poor performance, so omitting them from studies usually skews data in an overly positive light. 

Example 2 - Medical research 

The Survivorship Bias can also be observed in its impact on medical research. The Harvard Medical School and Beth Israel Deaconess Medical Center (BIDMC), attempted to conduct a study on trauma patients and to better their survival outcomes from different types of medical procedures. Due to the specific parameters of the study and skewed survival rates, the trial was only able to count 573 patients, out of their original 1502 participants. This study’s failure was due to survivorship bias, as the trial only included patients who had survived their initial injury, and who had then received care in the Energy Department before then receiving 4-8 blood transfusions.

How to avoid it

Once individuals learn about the Survivorship Bias, they can avoid bias by considering what data points may be missing from a dataset and using accurate data sources that do not omit key observations.

How Biases Can Color Entrepreneurial Decision-Making

This article explores the challenges faced by start-ups when they are venturing into new and unfamiliar territory. When it's time to consider a strategy shift, cognitive biases can creep in to promote fast and efficient decision-making. However, fast doesn’t always equate to better choices being made, sometimes failure to consider alternatives and “going with our gut” can lead to serious missteps.

Great Man Theory 

The great man theory states that leaders are born and not made. Meaning that there is some innate and intrinsic quality that makes certain people so influential. This theory also asserts that because of its inherent nature, those who are leaders deserve to be in that position. This article explores the claims and controversies, as well as how this theory connects to survivorship bias.