Dependency statistics in quotes (information theory, correlation and other feature selection methods) - page 12
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
The point is that the gamma distribution function appears in the article as if out of thin air, supposedly by solving a deterministic motion diphury - but not as a result of statistical or terversive analysis. Roman, so far I don't see any similarity in approaches to the solution - even conventionally.
But if you look closely, you can still find some similarity - say, in the word "distribution", which is also found in Yusuf's article :)
Alexey it's all clear... I just graduated from a basic university in 1999. And I, for some reason :-))), to ALL such curvilinear problems, especially when formulating tasks (TOR for writing EA) using them, I consider much the same approach when translating their solution into code... :-))).
But as I understand it - on this question of branch - ToR with their (curvulines) use is not formulated yet?
No, not articulated, that's for sure. They've only just started the alphabet (first grade), so it's a long way from real science here.
P.S. And I got my upper secondary education in 1987 and have already forgotten almost everything, except mathematics.
No, not articulated, that's for sure. They've only just started the alphabet (first grade), so it's a long way from real science here.
P.S. And I got my upper secondary education in 1987 and have already forgotten almost everything, except mathematics.
I see.
Wonderful. The Statistica package is the only source to go to for data mining. Therefore, TI should be forbidden to use it. And ban your own brain as well, because with Statistica it is no longer needed.
By the way I was referring not only to STATISTICS, but also to textbooks. Do not distort and pretend that you do not understand.
New knowledge cannot be gained without the strictest respect for existing terms and concepts recorded in textbooks.
You can't just take concepts from TI and call them Data mining. It is necessary:
define exactly what we take
justify the possibility of transferring it to a new ground
and prove the value of the result on the new ground in terms of this new ground.
HideYourRichess has been questioning the first point for a day, I do not see any intelligible answer for the last point.
That there are dependencies in quotients is not news, that there is memory is not news, there is a whole science called econometrics to identify them and use them in analysis and forecasting. And what have you found? Some lousy article that initially fails to define the place of the concepts used among other known and established concepts that you just need to sit down and learn, and if you know, make that knowledge public.
By the way referred not only to STATISTICS but also to textbooks. No need to twist things around and pretend you don't understand.
New knowledge cannot be gained without the strictest respect for existing terms and concepts recorded in textbooks.
You cannot just take concepts from TI and call them Data mining. It is necessary:
define exactly what we take
justify the possibility of transferring it to a new ground
and to prove the value of the result in terms of this new ground.
HideYourRichess has been questioning the first point for days, and I don't see a coherent response to the last point.
That there are dependencies in quotients is not news, that there is a memory is not news, for their detection and use in analysis and forecasting - a whole science called econometrics. And what have you found? Some lousy article, which initially did not define the place of the used concepts among other known and settled concepts, which you just need to sit down and learn, and if you know, then make this knowledge public.
there is no ground here. The method is extremely abstract. In simplistic terms: a discretised series of real instrument returns compresses (archives) better than a similarly discretised series of random walks. Why is another question.))
there's no ground here. The method is highly abstract. In simplistic terms: a discretised series of real instrument returns compresses (archives) better than a similarly discretised series of random walks. Why is another question.))
So when they manipulated data substitution with quantiles, they shortened the alphabet...(and enlarged the field of possible sounds).
like with no loss to the "average" ear.
;)
--------
going from five digits to three would be cool.
determine exactly what to take
justify the transferability to the new ground
and justify the value of the result on the new ground in terms of that new ground.
I don't argue, it all makes sense. Let's start with point 1.
1. "Define exactly what to take: First a cell task, then an indivisible task.
We fix an integer Lag. This will be the "distance between bars", i.e. the modulus of the difference of their indices on a given timeframe in MT4.
Objective: to determine whether there is a statistical relationship between the following two random variables: 1) the return of the "master" bar with index sh, and 2) the return of the "slave" bar with index sh+Lag.
This is what we take: all pairs of bars with a distance between them equal to Lag. The ultimate in accuracy.
faa1947 : HideYourRichess has been questioning the first point for days, while I don't see a comprehensible answer to the last point.
Where and what is there to doubt? Let's deal with the first point first. If we do, let's move on to the second point.
We fix the whole Lag. This will be "distance between bars", i.e. the modulus of difference of their indices on a given timeframe in MT4.
the task has changed...
o)
-----------
Given the conventionality of the timeframe bar. and its stable characteristics - because open & close are not characteristic. what's left is H & L.
what are we comparing? No one is giving us averages and cramps on the bar yet...
Shamanism...
Once again, I suggest that the famous Excel spreadsheets be posted here. otherwise as a remake of the famous universal... and other stuff - formula, we don't see it yet.
The lags of similarity are good. The criterion of similarity - we don't see it yet either.
so what's the argument-discussion about?
(