Technical Analysis Doesn't Work

ljyoung · Aug 8, 2007

It is not my job to "enlighten" the board. If you want to get into the gory details, then do so by all means. Knock yourself out. I see no point in what you are trying to do.

If someone wants to defend the pro TA side, they need to find counter evidence, not try to impress others by cutting and pasting an appendix out of the study. Such studies like this are put out for serious review by other institutions before acceptance. They are usually quite rigorous. They usually also publish limitations, observational methods, possible future research areas, references to other published studies, citations, etc.

If you have problems, then publish a counter study. Contact the author with your concerns and get him to update the study if you feel there are flaws.

That's just the point, rc. I don't want to get into the gory details if there's any possibility that a statistical cognoscenti can spare me the time and effort of doing so. Clearly that's not going to happen here. Impressing the members of this thread was not the purpose of the cut and paste job. If someone is going to blather on about science and statistics and what all this means to trading in the markets, it seems appropriate to ascertain on what basis they accept what has been published in the literature.

It seems rather obvious that the basis for your accepting this paper has less to do with what's in it and more to do with the simple, very simple fact that it was published. Is it your impression then that everything that gets published is without error? Hmmm?

There are many ways to address the arguments put forth by the non pro-TA crowd and I'm using one of them. I feel no particular desire to "publish a counter study" any more than you would feel inclined to publish a counter study. Correct me if I'm wrong.

As others and myself have said, it is the set of initial conditions which is most consequential when doing a purely statistical study. If the construct of your hypothesis is flawed then all the statistics in the world isn't going to change the fact that you've made something out of nothing.

Which is not to say that there are not some technical methodologies which are essentially useless but rather that your poor understanding of what it takes to produce a profitable technical protocol possibly amplified by prior personal failures at using the technical method, results in a singularly repetitive, bellicose and ineffectual effort to make your point.

lj

ProfLogic · Aug 8, 2007

If it can't be coded, your admitting its subjective. i have no issues with subjective approaches and believe they can work. but one needs to understand its subjective---unlike the proflogic types who claim absolute perfection with objective systems then fail to produce any proof of claims.

i'll admit its not luck, if the system can be TAUGHT to others with the same or similar results.
surf

__________________________________________________
You love to slam others then claim you don't. You are now and will always be a spineless unintelligent weasel.

I can back up everything I say but not to a rodent like yourself. That is a total waste of time and energy.

rcanfiel · Aug 8, 2007

Quote from kut2k2:

Nothing in my post indicates that money management creates edge. I explicitly said otherwise, in fact.

It is inane to say that (poor) "money management/position sizing can cause a profitable system to fail" (true) but then follow it up with "TA studies amount to shit because they are shit, it has nothing to do with money management."

TA studies amount to shit because they have lousy position sizing that destroys whatever edge they're trying to test for.

sorry, but traderdragon is correct.

Position sizing has nothing to do with TA. PERIOD. It has nothing to do with testing "complete" systems. You can position size a random system. Again, it has no relation.

Linking it in, as if it has anything to do with the validity of the study, shows a major lack of understanding. This is why I ignored the previous posts. They are groundless. I explained that in reply to your post, but it seems to have gone over your head.

rcanfiel · Aug 8, 2007

Quote from ProfLogic:

You love to slam others then claim you don't. You are now and will always be a spineless unintelligent weasel.

I can back up everything I say but not to a rodent like yourself. That is a total waste of time and energy. [/B]

Funny, you were complaining earlier about that I insult people.

You are one of the most insulting characters I have seen here. If you don't understand, back up and read your words. Except this time, you didn't shroud it by trying to use 4 syllable slurs that act above the fray.

rcanfiel · Aug 8, 2007

Quote from ljyoung:

That's just the point, rc. I don't want to get into the gory details if there's any possibility that a statistical cognoscenti can spare me the time and effort of doing so. Clearly that's not going to happen here. Impressing the members of this thread was not the purpose of the cut and paste job. If someone is going to blather on about science and statistics and what all this means to trading in the markets, it seems appropriate to ascertain on what basis they accept what has been published in the literature.

The basis is rigorous institutional reviews before these make it into the journals. I have participated in reviews and in studies. I don't get the feeling you have.

It seems rather obvious that the basis for your accepting this paper has less to do with what's in it and more to do with the simple, very simple fact that it was published. Is it your impression then that everything that gets published is without error? Hmmm?

Your grasp is weak.

There are many ways to address the arguments put forth by the non pro-TA crowd and I'm using one of them. I feel no particular desire to "publish a counter study" any more than you would feel inclined to publish a counter study. Correct me if I'm wrong.

As others and myself have said, it is the set of initial conditions which is most consequential when doing a purely statistical study. If the construct of your hypothesis is flawed then all the statistics in the world isn't going to change the fact that you've made something out of nothing. 

And as I said, most studies pass rigorous review by fellow institutions before publication. You are making zero points here if you are trying to paint it as flawed. They made very clear what the purpose and findings were.

Which is not to say that there are not some technical methodologies which are essentially useless but rather that your poor understanding of what it takes to produce a profitable technical protocol possibly amplified by prior personal failures at using the technical method, results in a singularly repetitive, bellicose and ineffectual effort to make your point.

well, at least you know how to string together long words.

kut2k2 · Aug 8, 2007

Quote from rcanfiel:

sorry, but traderdragon is correct.

Position sizing has nothing to do with TA. PERIOD. It has nothing to do with testing "complete" systems. You can position size a random system. Again, it has no relation.

Linking it in, as if it has anything to do with the validity of the study, shows a major lack of understanding. This is why I ignored the previous posts. They are groundless. I explained that in reply to your post, but it seems to have gone over your head.

What is being tested in these TA studies? Not TA. Trading systems based on TA.

Explain to us how you test any trading system while ignoring the position size.

Getting back to the coinflip example I posted previously: a skeptical researcher ignorant of probability decides to see there really is an edge. He bets every dollar in his possession. He flips a coin, gets a head. He is elated, having tripled his money. Again, he bets everything. He gets tails, and loses everything. He is now convinced that there never was an edge, and calls me a scam artist.

The fact that he risked more than the system merited never enters his head. The fact that those TA studies you worship are testing trading systems, not "TA in a vacuum", never enters yours.

NihabaAshi · Aug 8, 2007

Quote from marketsurfer:

If it can't be coded, your admitting its subjective. i have no issues with subjective approaches and believe they can work. but one needs to understand its subjective---unlike the proflogic types who claim absolute perfection with objective systems then fail to produce any proof of claims.

i'll admit its not luck, if the system can be TAUGHT to others with the same or similar results.
surf

Actually I didn't say something couldn't be coded.

I implied that system designers argue among themselves what can be coded and what cannot be coded.

Simply, it greatly depends on the skill of the programmer.

Thus, if one programmer lacks the skills to code a rule based method while another has the skills to code the same rule based method...

If both programmers don't know each other...one of them will surely argue that its subjective because it can't be coded.

Simply, just because someone doesn't have the ability to code a rule based method doesn't imply its subjective.

As for the luck issue, if a method (rule based or subjective) is taught to others and those others are able to become profitable after learning the method...

It's not luck even though the profitability isn't at the same level as the person that did the teaching.

In reality, the difference between the profitability of the teacher and the student is due to market experience.

Thus, I expect the student to achieve similar like profitability as the teacher when the student has the same amount of experience with the markets and with the method as the teacher.

Therefore, if I was using a method for 15 years...surely you don't expect someone taught the method 3 weeks ago to be able to produce similar like profits to determine if its LUCK or not.

Analogy, if Tiger Woods spent 2 weeks teaching you all the technique and tactics he uses in Golf...

Do you think you can go out tomorrow and win the British Open???

If you don't win or don't make the qualifying cut to play in the British Open...

Does that imply Tiger Woods performance level at the British Open is LUCK???

However, I do expect your golf to improve in those 2 weeks of learning from Tiger even if its just a little bit.

That little bit or small profit should tell you its not luck.

How about you learning Chess from a world rank chess master.

If he teaches you chess and you can't beat to local kid down the street in chess...

Does that mean the world rank chess master performance level is LUCK???

Therefore, I'm under the impression your the type that give no credit to market experience.

If you do see value in market experience...then your LUCK theory has no merits.

Mark

ProfLogic · Aug 8, 2007

Quote from rcanfiel:

Funny, you were complaining earlier about that I insult people.

You are one of the most insulting characters I have seen here. If you don't understand, back up and read your words. Except this time, you didn't shroud it by trying to use 4 syllable slurs that act above the fray.

Haven't looked much, huh.

When you know the circumstances of the comments I direct toward him and the history that surround their background then you may interject your opinions when asked for them. Since neither are the case, go back to commenting on those other things you no nothing about and stay out of conversations that do not concern you. It's obvious your parents didn't teach you that sticking your nose in where it didn't belong was rude. It's also obvious you do not do it in when you are out in public.

traderdragon2 · Aug 9, 2007

You clearly fundamentally do not understand the relationship between an edge and money management, stop the posing already, you already gave this fact away.

The quote below is so obviously wrong it doesnt even need to be debated. Might as well claim the moon is made of cheese.

TA studies amount to shit, because they are shit, not because of anything to do with position sizing.

Edge is easily tested for **WITHOUT ANY POSITION SIZING WHATSOEVER**.

Position sizing is applied after finding a real edge to ensure behavior acceptable to the trader, controlling real life slippage, max drawdown, risk of blowout, etc.

I wont debate this anymore. Real traders will agree with me and say DUH, the clueless posers will try to debate this non-issue.

TA studies amount to shit because they have lousy position sizing that destroys whatever edge they're trying to test for. [/B]

kut2k2 · Aug 9, 2007

Quote from traderdragon2:

TA studies amount to shit, because they are shit, not because of anything to do with position sizing.

Edge is easily tested for **WITHOUT ANY POSITION SIZING WHATSOEVER**.

Position sizing is applied after finding a real edge to ensure behavior acceptable to the trader, controlling real life slippage, max drawdown, risk of blowout, etc.

I wont debate this anymore. Real traders will agree with me and say DUH, the clueless posers will try to debate this non-issue.

Talking out of your ass doesn't make you a smartass, it makes you a dumbass.

The fact that you can't - yes, CAN'T - explain how you supposedly test for a trading edge without consideration of position size makes you nothing but a fool with delusions of cleverness.