Volumes, volatility and Hearst index - page 26

 
Candid:

Resilience is a characteristic that needs to be proven. One of the first candidates for stable structures (i.e. patterns) are repetitive structures. The highly correlated parts of the rada you mentioned are the repeating structures. At any rate, the patterns will definitely have a high degree of correlation and thus fall under your definition of similarity.

FA, to my understanding, interprets self-similarity in a much broader way.

I'll repeat the question - what is a pattern?
 
Paternus(Latin: Paternus) is a Latin name. Some famous bearers:
 
Candid:
Paternus(Latin: Paternus) is a Latin name. Some famous bearers:
What's the point of making a conversation like this? Pick one or the other.
 

To my surprise it turns out that the Russian-language Internet does not provide a more or less universal definition of the concept of a pattern. So I can't answer your question officially. :)

Proceeding from the translation, I propose to consider as a pattern any repeating extended formation.

And what do you understand by patterns?

 
Candid:

To my surprise it turns out that the Russian-language Internet does not provide a more or less universal definition of the concept of a pattern. So I can't answer your question officially. :)

Proceeding from the translation, I propose to consider as a pattern any repeating extended formation.

And what do you understand by patterns?

And how does MathCAD explain what we want? :о) I've already given part of the definition as part of what can be tested and will probably be useful for identification: "a stable structure that has a probable occurrence estimate". All that's left is to build this up with constraints, after which it will be impossible to move from there :o))))

 
Farnsworth:

And how does MathCAD explain what we want? :о)

For that we have to understand what we want first.
So you actually checked correlation of sites?

In principle, you can take it to a private matter, people may not be interested in these small details :)

 

Translation from English into Russian

pattern ['pæt(ə)n ]

  • 1. noun.
 
Candid:

To do that, we have to figure out what we want first.

Really? Why do you think I'm bothering you with formalism?

So have you actually checked the correlation of sites?

There is a mathematical theory about self-similar processes in FA that connects correlation, stationarity and similarity. Of course, and not only that I'm going to check, but I've already checked something. All in all, it seems that it is time to go back to FA again, it is a pity that time is short.

In principle, you could take it to a private matter, people may not be interested in these small details :)

In principle you can, but a little later, when the tedious specifics come in.

 

What, already migrated?

Translation:

1) a) pattern, model b) example (to follow), sample

2) a) model, pattern Syn: prototype b) pattern (in cutting and sewing) c) shape, model (for casting)

3) pattern, pattern (on matter, etc.)

4) a) system, structure; principle, model (of the organization of st.)

Which actually means, that the term has more of a figurative than an analytic sense. If Hurst is about 0.7-0.8, this is an indication of the trend character of the market. Nevertheless, though the trend is more likely to continue than to reverse, it will sooner or later reverse. The market, either persistent or counter-persistent, still has a stochastic nature and is therefore able to draw patterns, which, while not correlated with each other, still reflect a certain state of it. Like snowflakes, no two are alike.

My point is that it would be wrong to reduce self-similarity to repeating (i.e. highly correlated) patterns. The patterns are repetitive, but that doesn't mean the structures are repetitive. Take the two ascending ZZ segments. The correlation between them will be (on average) the same as the correlation between the ascending and descending segments. But the trend patterns will be similar.

 
Farnsworth:

There is a mathematical theory about self-similar processes within FA that links correlation, stationarity and similarity.


There must be a formal definition of self-similarity in this theory. I would like to see it.