Dependency statistics in quotes (information theory, correlation and other feature selection methods) - page 24
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
For once there's a decent topic...
I'd like to point out that all posts that questioned the decency of the thread have been ignored.
I understand your question correctly: "Explain to me what I don't understand (how to make a prediction one step ahead), but it must turn out the way I think"?
Do I understand your question correctly: "Explain to me what I don't understand (how to make a prediction one step ahead), but it must turn out the way I think"?
Well, the facts come first. If the methodology correctly detects the presence of regularities, then the question of applicability is removed, or rather transformed into a question of the limits of applicability. Opponents of "applicability in general" in this case it is more productive to look for errors in their reasoning, imho.
And really strange looks the desire to prohibit the discussion of the topic on the grounds that it is not in the textbooks. Imagine the person who poking in Bohr's nose the then textbook of physics forbids him to study quantum mechanics.
By the way, should employees of patent offices, for example, be allowed to do science?
GARCH, etc. they do not take into account many nuances such as the different cycles of the ox and many others.
Let me add to that and read your opinion. Besides GARCH, there are many ARCH models, each of which also have parameters. Therefore, what is there to discuss here?
Well, the facts come first. If the methodology correctly detects the presence of regularities, then the question of applicability is removed, or rather transformed into a question of the limits of applicability. To opponents of "applicability in general" in this case it is more productive to look for errors in the reasoning, imho.
And really strange looks like a desire to prohibit the discussion of the topic on the grounds that it is not in the textbooks. Imagine the person who poking in Bohr's nose the then textbook of physics forbids him to study quantum mechanics.
By the way, should employees of patent offices, for example, be allowed to do science?
Certainly, no one forbids anyone anything, this is too much on your part.
Niels Bohr has not yet been seen on this forum. Niels Bohr himself made his discovery using a scientific approach, which consists of some rules. The first one is a thorough discussion of the original, unprovable propositions. The second is not to use established terms in a new sense. Third, be sure to show the differences (if any) between the subject under discussion and existing theory and practice. If this is not the case, already the metaquotes that publish controversial things will not take up the article, let alone any serious publications, including patent offices.
If the methodology correctly detects the presence of a pattern, then the question of applicability is removed
That's the point: it's unclear what it detects: "information dependence" - I personally don't understand what it is. I tried to find it out from various angles, but got no answer. Some formula from TI is applied. The applicability of TI is also disputed. It is possible to remove the question of applicability only if it is found out what it is: a vegetable or a crocodile.
Certainly no one is forbidding anything, that's overkill on your part.
Niels Bohr has not been seen on this forum yet. Niels Bohr made his discovery using a scientific approach, which consists of some rules. First of these is a careful discussion of the underlying, unproven propositions. Secondly, you can't use established terms in a new sense. Third, be sure to show the differences (if any) between the subject under discussion and existing theory and practice. If this is not the case, already the metaquotes that publish controversial things will not take up the article, let alone any serious publications, including patent offices.
Well no one knew it was Bohr back then :). His postulates then had been discussed thoroughly and at great length.
You're not against terms, you're against the use of maths. It doesn't take long to come up with terms.
Well you yourself say that TI has never been used like this, that is you state the difference from the existing theory and practice).
If the methodology correctly detects the presence of a pattern, then the question of applicability is removed
That's the thing: I don't know what it detects: "information dependence" - I personally don't understand what it is. I tried to find it out from various angles, but got no answer. Some formula from TI is applied. The applicability of TI is also disputed. It is possible to remove the question of applicability only if it is found out what it is: a vegetable or a crocodile.
Well, the facts come first. If the methodology correctly detects the presence of regularities, then the question of applicability is removed, or rather transformed into a question about the limits of applicability. Opponents of "applicability in general" in this case it is more productive to look for errors in their reasoning, imho.
And really strange looks the desire to prohibit the discussion of the topic on the grounds that it is not in the textbooks. Imagine the person who poking in Bohr's nose the then textbook of physics forbids him to study quantum mechanics.
By the way, should employees of patent offices, for example, be allowed to do science?
Actually, the great Bohr, as well as the great Shannon, in solving their problems went from the essence, "physics", to figures, unlike what is happening here.
Second problem, it is not possible to explain to people who want to believe - that their belief is false. How it is possible to explain to people that the method is not applicable, as it is designed for stationarity and independence. Let even independence in the form of Markov chains, in any case it excludes applicability of method to data with presence of "memory" longer than that considered. Non-stationarity and dependence (I want to emphasize once again, this dependence is also non-stationary, therefore neither CM, nor conditional entropies work) directly follow from the understanding of market processes generating a quote flow.
Well no one knew it was Bohr back then :). His postulates then have been discussed thoroughly and at great length.
You're not against terms, you're against the use of maths. It doesn't take long to come up with terms.
Well you yourself say that nobody applied TI like that, i.e. you state the difference from the existing theory and practice).
Don't put things on me that I didn't write.
Either the postulates are fulfilled or there is nothing to discuss. With our remarks and HideYourRiches we try to move the apologists of the branch to fulfil these conditions, which are the same for everybody and everywhere.