The classic text-book example involves World War II bombers but instances arise in a variety of guises. Think of damaged war planes returning from combat. The clearest observation is that they are peppered with holes in their wings and tails. The immediate conclusion is to provide extra protection in these areas. But that’s an illogical inference. Observations are taken only on those planes that survived. The ones that didn’t return must also be included in the calculation. Hence, more protection for the engines!
Marketing managers have noticed survivorship bias in action for a long time. Sales people get agitated about the apparent success of competitor promotional mail campaigns. But they don’t see the failure rate and the number of disgruntled clients who hate receiving junk mail.
On the face of it, it seems effortless to become the next Bill Gates – don’t finish school; hang out in a garage and invest all your money in software dreams. But he’s one of the lucky ones. What about the millions who failed trying?
Engaging business owners often pay scant attention to clients who complain. “None of my other customers complain.” They take umbrage at the personal insult – failing to see that other clients haven’t bothered to complain – they have simply moved their business elsewhere.
All of these cases are examples of survivorship bias and our tendencies not to view the full picture when assessing any given situation. Naturally, finance is a further favourite area for this type of ill-judgement.
Many investment markets are made up of indices (groups of assets that are lumped together to form an index). The S&P 500 is perhaps the best well-known example. This index purports to contain the 500 largest companies in the U.S. – but that’s not the case. As expected, the size of any company ebbs and flows over time – getting bigger in times of acquisition and perhaps shrinking in bad times. It is, therefore, futile to measure the past performances of the S&P 500 because the actual 500 companies in question are not the same. What makes up the index today is a list of the companies that have survived over time and are larger for that success. To truly measure the performance of the S&P 500 one would have to include an assessment all of those companies that fell on hard times and dropped out of the top 500.
The repetitive mantra that past performance is not a reliable guide to future performance does not preclude survivorship bias. The warning, when repeated often enough, loses its effectiveness and unsuspecting consumers fall prey to scary preconceived notions. We all embrace success stories and the heroes that emerge. But remember, without failure there can be no success!