A purely theoretical question for mathematicians. With the possibility of moving to the practical plane. - page 9

New comment
 
Renat Akhtyamov:

ahhh...

By the way, the Internet is littered with such


Great, so. we're on the right track. Guide them to the correct interpretation of this expression, not forgetting the virtual prices. Please cite. the link you like best.

 
Yousufkhodja Sultonov:

Great, so. we are on the right track. Guide them in interpreting this expression correctly, not forgetting the virtual prices. Please give me the link you like best.

I don't like it, because econometrics doesn't work in financial markets.

a more advanced version of econometrics is now neural networks

no one has yet shown satisfactory results in neural network trading.

Prove otherwise by presenting practical trading results, and perhaps someone will start reading this whole piece of writing.
 
Сергей Таболин:

The series given in the first post is purely abstract.

The real series looks like this:

-1,202222222 0,378626831 -0,15119 0,249393 -0,31012 0,268994 -7,48 0,169875 -0,04285 0,19273 -0,03837 0,040593 -0,14868 0,059058951

or as follows

-36,06666667 22,33898305 -16,1776 23,19355 -21,0882 19,09859 -112,2 21,06452 -10,9688 20,81481 -10,3593 8,686916 -19,0313 12,69767442

The message was that any series can be continued by making assumptions about its "character".

Of course each of us can only make assumptions about those "characters" with which we are familiar. )))

Some believe that there are boundary conditions that give a "universal law", perhaps you have this information, formulate it. ))

The second question from your first post, unfortunately, is not clear to me at all. (

 
For some reason everyone immediately asks for a trading history when someone describes a method. What will it tell you? You don't need trading history to evaluate a method of analysis, you don't even need the market for that. What does the trading history give you, nothing? There are plenty of stories in the signals.
 
Aleksey Panfilov:

.......

Some believe there are boundary conditions that give a "universal law", perhaps you have this information, articulate. ))

The second question from your first post, unfortunately, is not clear to me at all.

  1. If I knew it, I would not ask it)))
  2. To find a pattern of change in one set and the second set. And also their mutual change.

 
Renat Akhtyamov:

no one liked it, because econometrics does not work in financial markets

a more advanced version of econometrics at present is neural networks

no one has yet shown satisfactory results for neural network trading.

Prove otherwise by presenting practical trading results, and perhaps someone will start reading this whole piece of writing.
Because neural networks cannot be used. Roughly speaking, neural networks are an averager. The essence of it is the profile learning model, and if there is a profile learning model, then anything is possible to use, including nerodets. If it were that simple, then Google, Yandex, Microsoft would have already conquered the markets, but ..... is not.
 
Сергей Таболин:

  1. If I did, I wouldn't ask )))
  2. Find patterns of change in one set and the second set. As well as their reciprocal changes.

  1. Find patterns of change in one set and the second set, as well as their reciprocal changes.
  2. What both sets have in common is an unexpected outlier of one of the values, which is not characteristic of the whole set, leading to an expansion of the range of possible BP values https://www.mql5.com/ru/forum/310338/page8#comment_11317182.
 
Maxim Romanov:
For some reason everyone immediately asks for a trading history when someone describes a method. What will it tell you? You don't need trading history to evaluate a method of analysis, you don't even need the market for that. What does the trading history give you, nothing? Vaughn's signals are full of stories.
Theory without practice - this is just horseshit, nothing more.
 
Renat Akhtyamov:
Theory without practice is just a lot of air pollution, nothing more.

But to move into practice, you have to develop a theory first. Or am I misunderstanding something?

 
Сергей Таболин:

But to move into practice, you have to develop a theory first. Or am I missing something?

A 100-page thread, not enough to publish an elementary econometric formula...

Another one...

12345678910111213
New comment
Reason: