Quote from AFJ Garner:
My recent work has been designed to penetrate the heart of this topic: I have discussed and back tested random entries at some length, I have queried the use of back testing and I have tried to explain why, over the past 40 years, trend following seems to have become increasingly difficult.
One of my contacts (a highly intelligent contact at that) holds that trend following is a dangerous illusion:
A âsingle threadedâ strategy, conceived by those deceiving themselves by believing that the market data is giving out "entry signals". While in the grand scheme of things they are just making random entries. The appearance of profitability is most often just âcurve fittingâ. In reality, in those cases, P&L is mostly oscillating around 0 (even though with large variance, large enough to create both dreams and defeats.)â
I am not sure that one can really describe a random entries system as a single threaded strategy. In many thousands of back tests I appear to have shown that entries coupled with a wide trailing stop seem to be profitable. It may be however that the very nature of trend following (running profits and cutting losses) is "single threaded" and a dangerous illusion?â
"Single-threaded" is a terminology that my contact uses to denote a "class" of strategies which have the following features: (1) There is one and only one "trade" at a time for each instrument (2) A "trade" is defined by an "entry" and an "exit". (3) Normally, entry is triggered by some "signal" and exit is triggered by "taking profit" or a stop ( the latter can be read as "taking a loss").
So to take that a stage further, my contact concludes that over the long term trend following is a zero sum game and an illusion fostered by curve fit back testing. And that if one conducted enough tests on random entries using a simple trailing ATR exit, the average CAGR would equate to zero. The same goes for any trend following system tested on a wide enough range of data â presumably necessitating the supplement of ârealâ market data by synthetic data.
So, does back testing on historic data have any validity at all? And if it does, can the reality of trend following be proved or disproved in empirical terms using past data?
I have sought to bolster my bias in favour of trend following rather than to destroy it. I sought to test out the theory that random entry, using a wide portfolio of instruments, coupled with a simple ATR based trailing stop would prove profitable using a statistically large sample size of test runs and trades. I thought to show that âcutting your losses and letting your profits runâ was a profitable strategy. But I can see how that may be thought of as a âsingle threadedâ approach.
Is any back testing approach which can shed any definitive light on this matter? Can it be proved or disproved, using past data, whether trend following is a profitable reality or a dangerous illusion?
If âproofâ is not possible one way or another, then back testing is indeed âa tool for foolsâ.
More of my ill conceived thoughts can be seen on my own website.
