Markets And Black Swans

February 28, 2007

The current global stock market turmoil handily demonstrates that market professionals and most of their customers don’t understand statistics.

Nassim Talieb wrote the definitive primer on market foolishness. To (over) summarize this excellent book, he explains that most market events are random, but that humans are hard wired to find patterns whether or not they exist, and these false patterns blind market operators to underlying truths.

So when an analyst says “The market went up because of XYZ”, he’s making an unprovable, and probably false, connection between XYZ and the movement – which most times is just noise.

Black Swans are events – like yesterday’s – which blow a hole in the consensus (in this case that markets would continue to rise). It’s the problem of inference first identified by David Hume, and elaborated by John Stuart Mill thus (p117, paperback):

No amount of observations of white swans can allow the inference that all swans are white, but the observation of a single black swan is sufficient to refute that conclusion.

So the longer a market has been rising does not effect the probability that it will tank tomorrow.

(Incidentally, scientists and pols who claim the debates on Global Warming, Darwinism etc are “over” are all ignoring or ignorant of this basic rule of inference).

Yesterday that black swan quacked (hissed? squawked?), and in spite of all the analysis, nobody really knows why – that’s why I follow Taleb and bet on black swans.

This is not – of course – financial advice.


Follow

Get every new post delivered to your Inbox.