Hearst index - page 39

 
faa1947: No, such a theory.

You're being overly categorical.

Published - no. But that doesn't mean it doesn't exist at all.

 
Mathemat:
It's there, but who's going to do it here?

I'm doing it. But not Hearst))
 
Mathemat:

You're being overly categorical.

Published - no. But that doesn't mean there isn't one at all.


That's right. In general, I am convinced that not all knowledge is worthy of humanity, some is better kept for the time being.)
 
alsu: I do. But not Hurst))
I didn't mean you, Alexei : )
 
alsu:

Regression can be built on anything, and this method is called the rule of thumb. The question is whether we can say in advance that of the many possible regression models, this one will better describe the behaviour of the quotient for some reasons. Describe these reasons mathematically. Write a difference equation, calculate the regression coefficients analytically - so that it is clear which ones represent the influence of external factors, which ones characterize the internal properties of the system, and which ones combine internal and external factors.

Try, for example, to construct a difference equation of one of the simplest systems - an oscillating circuit. In regression terms this will be an ARMA model and its coefficients will be a combination of parameters of the circuit itself and the input signal:

Y(k) = 2*a*cos(w0)*Y(k+1) - Y(k+2) + X(k) - a*sin(w0)*X(k+1)

Here X is unknown external influence, Y is observed response, a is damping parameter, w0 is natural frequency of vibration

I completely agree with you.

Any line of symbols and any result must have economic sense. Otherwise it's just a numbers game (gambit method).

The original notation must be based on an understanding of the economic essence. If we have included the cyclical component, we must verbally, meaningfully explain where it comes from. Or we can say that we will not do it, for example in Forex, but we will do it in the "oil=gasoline" pair trading.

Nevertheless, this does not eliminate the problem. Tests for missing variables and for redundant variables in regression equation are known.

Generally speaking, having a toolkit, no matter TA or matstatistics, does not remove the problem of experience and intuition. This is what determines, allows us to identify the important and stable factors and relationships and to neglect the secondary ones. Unfortunately, or rather fortunately.

 
Mathemat:

You're being overly categorical.

Published - no. But that doesn't mean there isn't one at all.

I can repeat my position.

I am not interested in dissertations - I have had enough, for many years. Only practice. And in a practical sense, there is so much that exceeds my capabilities. There is a lot of dull monotonous work, you need teams of people.

 
faa1947:

However, this does not eliminate the problem. Tests for missing variables and for redundant variables in the regression equation are known.


It does not remove the problem, but it does simplify it. In the above example, you can see that the equation imposes restrictions on the model coefficients: they can no longer be whatever you want, but must satisfy the following conditions

A1 = 2*a*cos(w0), A2=-1, B0 = 1, B1 = - a*sin(w0)

That is, the mere assumption about the internal structure of the system (loop) makes it possible to reduce the number of degrees of freedom in a regression model from 4 to 2. And such a model is easier to fit the observed data in an attempt to identify parameters (easier in terms of the result; calculations, of course, will become a bit more complicated - we will have to use a non-linear regression, since dependence on the parameters is non-linear)

Thus, the fundamental model is needed in order to reduce the dimensionality of the problem, which simplifies the search for parameters and, ultimately, makes it more likely to correctly answer the question of whether the model is adequate at all (whether there is a set of parameters satisfying the available observables).

 

You've got a lot on your mind.

Shooting sparrows out of guns.

There is a state of the market, it has been called overselling since the dawn of time.

There are bulls and bears who have eyes and can see this condition.

Both are in a tight interest environment with their own opportunities and tactics.

And the real ratio of currencies that NO ONE knows.

The methods are a wagon and a small cart, but the ratios on the above HOW to calculate?

All the maths has to be calculated with coefficients, corrected for wind, like in artillery.

An object in the sight does not guarantee a hit.

 
Dersu: There is a state of the market, it has been called over-selling since the dawn of time.
It is a fiction. In any case, I don't know any indices which more or less reliably show it on forex. Even taking into account Level II, in which some people want to see a panacea.
 
Mathemat:
It's fiction. Anyway, on forex I don't know of any indies that show it more or less reliably. Even with Level II, which some want to see as a panacea.



I totally agree.

Moreover, recall the change in blade position by the supposedly blind samurai before striking the mercenary.

Just tweak the secondary currency's quotient and the picture is "sailed".

And the mercenary did all the maths.

This is war. And you don't take prisoners.