Ladies & Gentlemen: Please prepare your responses.

Discussions about the testing and simulation of mechanical trading systems using historical data and other methods. Trading Blox Customers should post Trading Blox specific questions in the Customer Support forum.
Post Reply
adamant
Roundtable Knight
Roundtable Knight
Posts: 118
Joined: Mon Aug 25, 2008 1:20 am
Location: Norway

Ladies & Gentlemen: Please prepare your responses.

Post by adamant » Mon Oct 19, 2009 11:08 pm


sluggo
Roundtable Knight
Roundtable Knight
Posts: 2986
Joined: Fri Jun 11, 2004 2:50 pm

Post by sluggo » Tue Oct 20, 2009 12:00 am

Sometimes the SSRN firewall "siezes up"; if so, and you temporarily can't see the referenced paper, here's its title and abstract. (Notice that the authors assume, without stating, that technical analysis is applied to stock trading.)

Technical Analysis Around the World: Does it Ever Add Value?

Ben R. Marshall*, Rochester H. Cahan, Jared M. Cahan Massey University New Zealand

Abstract Technical analysis is not consistently profitable in the 49 countries that comprise the Morgan Stanley Capital Index once data snooping bias is accounted for. There is some evidence that technical trading rules perform better in emerging markets than developed markets, which is consistent with the finding of previous studies that these markets are less efficient, but this result is not strong. While we cannot rule out the possibility that technical analysis compliments other market timing techniques or that trading rules we do not test are profitable, we do show that over 5,000 trading rules do not add value beyond what may be expected by chance when used in isolation.

-w.
Roundtable Fellow
Roundtable Fellow
Posts: 95
Joined: Wed Nov 19, 2003 11:02 am

Post by -w. » Tue Oct 20, 2009 7:22 am

We cannot rule out the possibility that technical analysis can be used to compliment other investment techniques, or that trading rules other than the ones we examine are profitable.
"Investment techniques" such as position sizing and portfolio allocation maybe? As long as most people still focus on finding the one perfect signal all is not lost for systems trading I think.

adamant
Roundtable Knight
Roundtable Knight
Posts: 118
Joined: Mon Aug 25, 2008 1:20 am
Location: Norway

Post by adamant » Tue Oct 20, 2009 5:46 pm

Superficially, I think it would be terribly naive to think any single indicator is the holy grail - and that testing 5000 rules to see if one might be is probably a relatively unproductive idea in the first place.

More seriously, I think you are both on the money with your initial points.

J D Canning
Roundtable Fellow
Roundtable Fellow
Posts: 74
Joined: Thu Jul 03, 2008 6:35 am
Location: Surrey, UK
Contact:

Post by J D Canning » Wed Oct 21, 2009 12:24 pm

It would be very interesting to hear these academics' views on the historical performance of well known mechanical system traders who we all know and love. Are they just lucky? Consistently and profitably lucky over a period of 20 years and more? Are they the winners in the survivorship bias game? Perhaps they are a statistical aberration?

In any event I am sure they will have a very elegant answer based on sound economic theory. And economic theory, lest we forget, gave us the wonder that is the Efficient Market Hypothesis. And what a thing of beauty that turned out to be...

adamant
Roundtable Knight
Roundtable Knight
Posts: 118
Joined: Mon Aug 25, 2008 1:20 am
Location: Norway

Post by adamant » Wed Oct 21, 2009 5:02 pm

As a graduate student in economics I can only agree with you. Surely the professors will come up with a model ripe with assumptions that support their initial biases and as a result successfully removes the whole discussion from the real world.

Actually, several studies have been published in the last thirty years that dismantles the EMH in my view. Lo at MIT and McKinley at Stanford(I think) have found that (and this study applies only to stocks) stock market returns are non-random. Mebane Faber has shown that technical tools can improve risk adjusted returns over the last hundred years. Park and Irwin have reviewed the literature on TA profitability and found that 58/92 studies showed TA actually added value (even after subtracting the ones that do not account for data snooping biases or underestimate slippage and comish, you would end up with many supportive pieces).

Of all these studies, only very few have been published in mainstream academic journals. I wonder why.

-w.
Roundtable Fellow
Roundtable Fellow
Posts: 95
Joined: Wed Nov 19, 2003 11:02 am

Post by -w. » Thu Oct 22, 2009 4:57 am

... historical performance of well known mechanical system traders ...
I think it's important to not equal mechanical systems trading to technical analysis. While systems traders obviously do make use of TA, many if not most users of TA do not trade systematically.

In my opinion, performance comes from the process and not from the tools. Even the best tools will not help you if you don't use them whithin a more or less intelligent framework. But to develop that framework you need way more than a couple of high probabilty entry exit signals.

babelproofreader
Roundtable Knight
Roundtable Knight
Posts: 138
Joined: Wed Nov 10, 2004 4:36 pm

Post by babelproofreader » Thu Oct 22, 2009 5:41 am

The study makes the claim that profits accrued from TA studies are statistically indistinguishable from profits that could be expected from the null hypothesis investment strategy. It does not claim that TA studies are actually unprofitable.

rabidric
Roundtable Knight
Roundtable Knight
Posts: 243
Joined: Mon Jan 09, 2006 7:45 am

Post by rabidric » Thu Oct 22, 2009 11:18 am

lol . statistically distinguishable is a whole subtopic in itself. all depends on how strongly you distinguish and on what basis. A black-hole of a topic if ever there was one.

Post Reply