Enough already! It's not random

[kut2k2]

Quote from MAESTRO:

You started the post, you have made a false statement, you exhibited no understanding of the subject, you failed to comprehend the math, you were unable to see the hard evidence that I have already provided and now you are trying to use someone else's posts to back up your infantile theories? Stop embarrassing yourself and go back to school, read some books develop some knowledge then come back prepared and we will talk. My goal is education but I only provide knowledge to the ones who want it. You clearly are ignorant and unwilling to learn, so no efforts from me will change your thick head. Useless!

MAESTRO
02-22-08 09:51 AM

"At any point of time the probability of the trend to continue or reverse is still 50/50. Price patterns are for idiots who have no education. It is a religion and as any religion it has rituals – one of them is trend!"

What you and your supporters are too stupid to realize is that the average return has nothing at all to do with daily direction, which YOU insist is 50/50.

Instead of hiding behind others to ineptly argue for you, why don't you man up, admit you were wrong, and actually face the fact that the S&P daily direction is nonrandom? It isn't 50/50, as you arrogantly and foolishly lectured us on. And even if it's 1315/1197, the run sequences still aren't random.

Too bad if the truth embarrasses you but, hey, this is ET, maybe one day you'll be man enough to actually play with the people here who think for themselves.

 

[sjfan]

Quote from kut2k2:


All it tests for is randomness, and it didn't find a reasonable degree of randomness in the S&P 500 for the ten years that ended last year.

Sigh indeed. no, if you had any statistical training, you will realize that this is not at all what the test is saying. The test is saying that with high confidence it rejects the notional that the directional moves of the S&P day-on-day is independent of each other. That is to say, the S&P is serially correlated.

Serial correlation does not imply no-randomness. In fact, there's a host of random generators are do exactly that.

Please - go read a book.

 

[MAESTRO]

Quote from kut2k2:

MAESTRO
02-22-08 09:51 AM

"At any point of time the probability of the trend to continue or reverse is still 50/50. Price patterns are for idiots who have no education. It is a religion and as any religion it has rituals – one of them is trend!"

What you and your supporters are too stupid to realize is that the average return has nothing at all to do with daily direction, which YOU insist is 50/50.

Instead of hiding behind others to ineptly argue for you, why don't you man up, admit you were wrong, and actually face the fact that the S&P daily direction is nonrandom? It isn't 50/50, as you arrogantly and foolishly lectured us on. And even if it's 1315/1197, the run sequences still aren't random.

Too bad if the truth embarrasses you but, hey, this is ET, maybe one day you'll be man enough to actually play with the people here who think for themselves.

You know, I just realized that arguing with you is not fare. It’s like biting up a 5 year old boy. I always thought that a grown up man have to exhibit mercy. I think you embarrassed your self enough and all the people that read your posts already realized it. So, I won’t make it worse. Good luck to you! Happy trading!

 

[kut2k2]

Quote from sjfan:

Sigh indeed. no, if you had any statistical training, you will realize that this is not at all what the test is saying. The test is saying that with high confidence it rejects the notional that the directional moves of the S&P day-on-day is independent of each other. That is to say, the S&P is serially correlated.

Serial correlation does not imply no-randomness. In fact, there's a host of random generators are do exactly that.

Please - go read a book.

So you think random walk theory supports serial correlation. Yes, you should go read a book.

 

[pneuma]

Quote from fearless9:

You have all proved a point and it has nothing to do with random. Quite the opposite in fact.

All you wonderful theoreticians have completely failed to connect this thread to the noble ART of making money from the markets.

Humm, I tend to agree.

I personally don't care if the market is random or not. My profit curve is in a significant up trend, and has been for quite some time now. Let them argue the semanics and we'll just get on with the making money.

How can I put this succinctly - there is more than one way to screw the goose, but the important thing is: are you getting your dick wet?

pneuma

 

[sjfan]

Quote from kut2k2:

So you think random walk theory supports serial correlation. Yes, you should go read a book.

Random walk isn't the only form of randomness, you know. You know that, right?

 

[Slave2Market]

Quote from MAESTRO:

Please read the paper attached that I wrote about 5 years ago.
I have a little hope that you will actually understand it, but who knows ...

I read your word document with interest, but the same type of Gaussian distribution is obtained by simply detrending the daily close prices of the S&P 500? As I'm sure you are aware, this can be done in a myriad of ways e.g. Log(Close Today/Close Yesterday), linear regression, dividing the close by a moving average, etc. There are many ways to detrend data, but I usually opt for a simple method.

Could you elaborate as to why you feel normalizing by the ATR results in a different perspective? I’m not sure what period you used for the ATR, but I got similar results by dividing the close by a 10 or 20 period ATR.

The "Fat Tails" of the distribution are present no matter what method one uses ... unless they are specifically excluded.

As to whether the detrended distribution is the result of a random or nonrandom process ... I'm not firmly entrenched in either camp, but I do believe that the real opportunities are in the "Fat Tails"!

Regards,

Slave2Market

 

[kut2k2]

Quote from sjfan:

Random walk isn't the only form of randomness, you know. You know that, right?

I believe we're basically in agreement here. I wasn't arguing that price has no random component; that would be silly. My attack was on random walk, which says that price is fundamentally random, even with a drift component. You and I both recognize the serial correlations, which are anathema to random walkers.

 

[toc]

It's random, but only for idiots!

 

[Diamond Geezer]

"This is an asanine argument to have and keep having and a real waste of time. Who gives a shit if it is random or not. All that matters is if you can make money. The rest is bullshit and why does convincing some else to think like you matter. I guess if you are not making money then ACADEMIC discussions are perfect for all of you."

Your anti-intellectual "cred" is now well established Mike-whatever

How do you feel about knowing how to calculate a simple average? How's about something more advanced like say a standard deviation? Is it academic bs too?

The stuff they're talking about is admittedly a little more advance than 1+1 =2 but it's used to find trading edges.

Academics are'nt hired to be traders but they put out useful raw material to build upon. Hating them says something about oneself. (PS I'm not an academic)