While reading an article titled The Trough of No Value this passage caught my eye:
I have to chuckle whenever I read yet another description of American frontier log cabins as having been well crafted or sturdily or beautifully built. The much more likely truth is that 99% of frontier log cabins were horribly built—it’s just that all of those fell down. The few that have survived intact were the ones that were well made. That doesn’t mean all of them were.
I think it’s a marvelous illustration of survivor bias (also known as survivorship bias), itself a type of sample bias.
We should always look for implicit selection pressures that could have biased our sample and made it non-representative of what we’re trying to measure. For example, only the best music from the 1800s has survived to this day – most of the mediocre pieces have been long forgotten – so listening to music from that era that has survived to this day can’t give us an accurate portrait of the whole range of music produced of the 1800s.
It’s the same with mutual funds (those that perform badly are eventually shut down) or with ‘antique’ furniture (to be preserved, pieces usually have to be old and attractive).
See also: Articles on Rationality