Mental pitfall: Survivorship Bias

February 1st, 2008

Share |

Today, we will continue with the series on common mental pitfalls that can lead to fallacious reasoning (see Common mental pitfalls that leads you astray for a compilation of this series of articles).

The topic we will cover today is Survivorship Bias. To give you a clear idea of this mental pitfall, let us give you a story. Suppose we sent a letter to 1000 people, telling them what the stock market will do the next day. We told 500 of them that stock prices would fall the next day, and tell the other 500 that stock prices would rise. Lo and behold, stock prices fell the next day. So, we sent a second letter to those former 500, telling them what the stock market will do on the third day. We told 250 of them that stock prices would fall on the third day and the other 250 that stock prices would rise. Lo and behold, stock prices rose on the third day. So, we sent a third letter to the latter 125, telling them what the stock market will do on the fourth day…

We repeat this trick again and again until there is only 5 of them left. Later on, someone interviewed those 5 ‘survivors’ and ask them for an opinion of our stock tip letters. Lo and behold, they reckoned that we are incredible prophets who can accurately predict what the stock market will do.

For someone assessing our stock market prediction ‘performance’ through those 5 ‘survivors,’ his conclusion from that assessment will be biased. It is inconceivable to him that our predictive ‘track record’ is merely the product of 100% luck. As the Wikipedia says, Survivorship Bias is the

… tendency for failed companies to be excluded from performance studies because they no longer exist. It often causes the results of studies to skew higher because only companies which were successful enough to survive until the end of the period are included.

For investors, this mental pitfall can result in erroneous decisions. As the Wikipedia continues,

For example, a mutual fund company’s selection of funds today will include only those that have been successful in the past. Many losing funds are closed and merged into other funds to hide poor performance. This is how 90% of extant funds can truthfully claim to have performance in the first quartile of their peers: the other three quarters of funds have closed.

In Nassim Nicholas Taleb?s book, The Black Swan: The Impact of the Highly Improbable, he wrote:

The reference point argument is as follows: do not compute odds from the vantage point of the winning gambler, but from all those who started in the cohort… If you look at the population of beginning gamblers taken as a whole, you can be close to certain that one of them (but you will not know in advance which one) will show stellar results just by luck. So, from the reference point of the beginning cohort, this is no big deal. But from the reference point of the winner (and who does not, and this is key, take the losers into account), a long string of wins will appear to be too extraordinary an occurrence to be explained by luck.

In the same way, if a salesman of a stock tip-sheet tries to persuade you to part your money by showing you its glorious ‘track record,’ think again. If you can see all past and present stock tip-sheets (including the ones that are currently defunct), you will surely not be so impressed by this one’s ‘track record.’

So, do not let survivorship bias fool you!