Random Flow Theory and FOREX - page 81
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
Found the present, thanks Sergey and really fascinating=)
Evening, please tell me where to look... I searched the whole site, but did not find it... Analytics have not looked, frankly, because there is a lot of it...
Good evening, can you tell me where to look? I've searched the whole site, but haven't found it... I haven't looked at the analytics, to be honest, because there's a lot of them...
Answered in private...
A great thread!
> Of these 650 people who stupidly looked at the size and thought cool indicator or something, out of ignorance, purely for the sake of interest, this does not mean that they have consciously downloaded it to continue to work with it and develop, although I do not dispute that the product is cool, I just mean that apparently all the same am right, because if 700 people downloaded it consciously, then perhaps someone still has started a discussion with you, but no, why not know (?), Although I too would be interested to understand it. But alas, we are not counts.)
I'm one of the remaining 50... =0)
There is a question like this: Inchaos theory, the correlation integral is the average probability that states of the system at two different moments of time seem to be close, and in R there is a realization of this integral? And if so, how to use it?https://ru.wikipedia.org/wiki/
and here is another interesting one to readhttp://chaos.phys.msu.ru/loskutov/PDF/Lectures_time_series_analysis.pdf
near a phase transition or a critical point, fluctuations of any scale take place, and therefore, one should look for an explicitly scale-invariant theory to describe these phenomena
A classy branch!
It sure is.
There is a question like this: Inchaos theory, the correlation integral is the average probability that states of the system at two different points in time seem to be close, and in R there is an implementation of this integral? And if so, how is it used?https://ru.wikipedia.org/wiki/
The correlation integral can be used to determine the correlation dimension of an attractor of the system, see the example here. And this, in turn, is related to other characteristics of the fractal...
near a phase transition or a critical point, fluctuations of any scale take place, and therefore, one should look for an explicitly scale-invariant theory to describe these phenomena
Exactly.
The correlation integral can be used to determine the correlation dimension of the attractor of the system, example here. This, in turn, is related to other characteristics of the fractal...
... or almost. The processes at different scales are similar, but they don't seem to be exactly the same.Hey, that's annoying. Can I answer that?
It could be simpler than that. I won't answer that.
No, you don't.)
Thank you for your reply. There is nothing in your example about using R to calculate the correlation integral and its value in the context of the example is picked up as a dimension... It's not clear... After all, the correlation integral is the average probability that the states of a system at two different points in time appear to be close ( not exactly the same )... It seems to me that calculating such an integral requires comparing 2 matrices of the same dimensionality with normalized data...
The point is that this probability is the greater the greater we have taken the size of the relevant neighborhood (this seems obvious). This dependence, if it has a power law character, then its exponent is just called the correlation dimensionality.
In the real situation, the integral is approximated by the sum at different diameters of the neighborhood, then the corresponding dependence is plotted, logarithmically, a linear segment is selected and its slope is taken; this is the estimation of the correlation dimension.
Calculation of CI in R is in this package, but in general I strongly advise to use www.rseek.org to find the required functions.
I would like to clarify if I have understood correctly:
"the integral is approximated by a sum at different diameters of vicinity, then the corresponding dependence is plotted" in the local language sounds like "a graph is plotted at different timeframes" ? Then it is logarithmed - something like ln(OPEN) [actually normalization?]
then "linear section is highlighted" = we highlight the "trend" [also vague]. Can you elaborate on that?