A purely theoretical question for mathematicians. With the possibility of moving to the practical plane. - page 4
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
Let's do it a little differently.
Here's not a zig-zag. Purely visually connected the tops of the "trends".
Here is without any knees at all.
I would like to calculate the interdependence of price movement on the marked segments.
The zig-zag has been cited purely for clarity. Sorry again, I'm not a mathematician, I'm not familiar with special terms.
Thank you. I understand you. I look forward to understanding in return - no more comments like that. OK?
Start simple, with basic visual statistics.
Construct a 3-dimensional histogram of the zigzag (you can do it in Excel) - in X time with an accuracy of 10 (for example) bars, in Y - the high-low difference with an accuracy of 500 points, in Z - how many times it occurred.
Then you may make samples by conditions - the same thing, but provided that the previous move of the zigzag is at least 1000 points.
and so on...
Algebra I think you can not help here, just take the correlation formula.Correlation coefficient by Pearson or Spearman. They will tell you if there is a correlation or not. To be able to calculate the series you need a hypothesis formula and then check its convergence or non convergence.
In this case it is the formula for finding relationships in a chain of given values that is needed. I do not believe that this is an unsolvable problem. And after that you can build, as you said, formula-hypothesis and check it.
In this case it is the formula for finding relationships in a chain of given values that is needed. I do not believe that this is an unsolvable problem. And after that you can build, as you said, formula-hypothesis and check it.
So take Pearson's or Spearman's formula, it is impossible to describe them here (on the forum) - there is no symbolism))
So take Pearson's or Spearman's formula, they cannot be described here (on the forum) - there is no symbolism))
Can I get the link?
And there is no way to decompose this formula into simpler components? )))
Can I get a link?
And can you decompose this formula into simpler components? )))
https://ru.wikipedia.org/wiki/%D0%9A%D0%BE%D1%80%D1%80%D0%B5%D0%BB%D1%8F%D1%86%D0%B8%D1%8F You must have values from the two columns n1 - m1 \ n2 - m2 \...etc, and at least 6 values.
So take Pearson's or Spearman's formula, they cannot be described here (on the forum) - there is no symbolism))
They have already been described here dozens of times
https://www.mql5.com/ru/search#!keyword=spearman
+ The keyword=spearman and the English code base - if not enough will be enough.
SZS: somewhere was still a library of R - there should be ready-made, Alglib surprised me, there is no it - checked the first
They have been described here dozens of times
https://www.mql5.com/ru/search#!keyword=spearman
+ english code base - if not enough
ZS: somewhere was still a library R - there should be ready-made, Alglib surprised me, there is no it - checked the first
I have a good working relationship with Spearman.
you can, but not for all series, study
this is number theory - a branch of mathematics that deals simply with mathematical manipulation and the search for patterns between numbers (rows)
In this case, what is needed is a formula for finding relationships in a chain of given values. I do not believe that this is an unsolvable problem. And only after that you can build, as you said, formula-hypothesis and check it.
There is no such magic formula. You just have to look for a pattern. You have to select one plot, look for it in the whole story and see if it corresponds to the continuation. And so on with all the pieces of data.