By: rael on Giovedì 05 Settembre 2002 12:35
Nick Perry su ^Schaeffer Research#http://www.schaeffersresearch.com/sentiment/observations.asp?ID=6095^ con molta pacatezza mette in guardia dallo studio statistico dei mercati.
Cosa ovvia, certo!
Ma forse nemmeno tanto.
--------------------------
Today I'm revisiting a book that's been mentioned in previous market commentaries. It's called Fooled by Randomness and the author is a hedge fund operator named Nassim Nicholas Taleb. If I kept a "Top 10" list of books, this would be one of them. I want to point out that this is NOT a book that details trading strategies or gives explicit investment advice. Instead, I believe it's meant to open up your view of the world. I think it's important to occasionally take a step back from the deluge of stats and numbers we get everyday and try to put things in perspective.
About half way through the book, Taleb explores the concept of the "black swan:"
In his Treatise on Human Nature, the Scots philosopher David Hume posed the issue in the following way (as rephrased in the now famous black swan problem by John Stuart Mill): 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.
Taleb expands on this concept in the next few paragraphs and arrives at the following conclusion:
I can use data to disprove a proposition, never to prove one. I can use history to refute a conjecture, never to affirm it. For instance, the statement "The market never goes down 20% in a given 3-month period" can be tested, but it is completely meaningless if verified. I can quantitatively reject the proposition by finding counterexamples, but it is impossible for me to accept it simply because in past data the market never went down 20% in any 3-month period.
On the following page, the author shows the flaws of back-tested data with a humorous example involving President Bush. But I won't ruin the surprise for those who want to read the book.
My reason for quoting this author today is to encourage you to look beyond the daily data. History can serve as a guide, but by no means is it a template of what has to occur. Another book that's quoted extensively in these pages is Trading in the Zone by Mark Douglas. In this book (which would also make my "Top 10" list), Douglas states the fundamental truths of trading. His number one rule is that "Anything Can Happen."
Taleb uses the black swan to illustrate how what isn't shown by the data can be just as important as what is shown. When I first started trading, I created a mechanical trading system and back-tested it over several years of data. The system seemed to be infallible. I was discussing it with the trading manager and he asked me how it would perform under a given hypothetical situation. Since this situation wasn't in the back-tested data, I responded that it couldn't happen. We went round and round about it. I pulled out piles and piles of data to prove my point. At the time, I couldn't understand that, as a trader, you need to consider the scenarios you don't see. I began to trade the system and, as if on cue, an unanticipated environment caused the flaws to become evident. As is the case with trading, lessons aren't truly appreciated and learned until you go through them. Luckily for me, this lesson was encountered early ... when the damage was minimal.
Think of today's commentary as a friendly reminder to always be aware of what the data doesn't show.