# Zero sample correlation does not necessarily mean there is no linear relationship - page 53

tara: That's what you're all about.

There you go, the snapping...

I'm not all about that, I assure you.

I don't get it in a big way.

What do all these random processes have to do with the Integer figure, which is y=a+bx forever and ever.

And to apply the knowledge in random processes we should subtract the straight line from the digital representation of the figure and look at the result. If it's pure zero, that's one thing, if it's not zero, that's another. But one should always do smoothing (sometimes called detrending). There is no point in discussing the randomness of the data if there is a deterministic component to it, and if judging the figure by eye, then if there is a random component, it can be neglected. And forum people are trying to calculate something about randomness. It is necessary to perform smoothing and investigate the residual.

EconModel:

I don't understand it in a big way.

There is no point in discussing the randomness of data if it has a deterministic component,

)))))All random variables have a deterministic component, which is what distinguishes them from uncertain quantities. It is mat statistics and econometrics that separates the deterministic component from random variables.

Generally speaking - it is possible and necessary to calculate QC using the initial data (prices) of the Forex market. QC can and should be calculated on non-stationary series. QC for stationary and ergodic series is not needed at all - everything is clear and understandable for them.

НЕ совсем знают как применить рецикл в практической тоговле на валютном рынке , рецикл нужен для нахождения в частности наиболее устойчивых (менее подверженных изменениям) динамических систем ,которые являються не чем иным как валютными портфелями

So for today and for the next 2-3 months such a portfolio is a simultaneous purchase of NZ, Pound, Aussie against the Yen, Euro, USD

Demi:

)))))All random variables contain a deterministic component, which is what distinguishes them from uncertain quantities.

So what deterministic component do you think is contained in white Gaussian noise?

In a big way - QC can and should be calculated on the raw data (prices) of the forex market.

Suppose you have calculated the ACF of the price (not increments) of some instrument on D1 over the last 5 years, and you see that it is positive with a 10 day lag. Can you build a profitable strategy based on that? :D

Integer:

So the row is stationary... So you can't use it that way, but only the first differences. Let's imagine another row, exactly the same, and another one, only the line is pointing downwards.

So, the correlation is perfectly calculated, when both series are directed in one direction - we get 1, when they are directed in different directions - we get -1. I.e. the result makes sense, the correlation is calculated, and the value corresponds to reality.
However, the series are non-stationary, so you can't do it that way:) you have to read the correlation from the first difference. So we have series 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 and -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 - on such data the correlation cannot be calculated.

That's it! Gentlemen

* * *

I searched the internet a little on Granger, and there I met statements that Granger method should be applied only on the first differences... However in more competent textbooks there is no such thing, on the contrary it is written, that on stationary data another method is applied. But with what aplomb everyone proves their point... I don't know, it's obvious to me that I don't need any first difference.

* * *

All is clear with gentlemen econometricians and the like... Therefore, I take my leave and do not participate in conversations on the subject of correlation, etc.

In addition to manipulating formulas and terms, you need to understand the essence and meaning.

Integer:

I have searched the internet a bit on Granger, and there I met statements that Granger method should be applied only on the first differences... But there is no such thing in more competent textbooks, on the contrary, it is written that a different method is applied on stationary data. But with what aplomb all prove their rightness... I don't know, it's obvious to me that I don't need any first difference.

One should not read "speeches" and "competent textbooks" but the description of the method in the original.

http://webber.physik.uni-freiburg.de/~jeti/studenten_seminar/stud_sem_SS_09/grangercausality.pdf

Part 5, paragraph 1. Enjoy.

[Deleted]
Integer:

That's it! Gentlemen

In addition to manipulating formulas and terms, you have to understand the essence and meaning.

Hang on. Now the flapjacks will fly ))))

anonymous:

Suppose you have calculated the ACF of the price (not the increments) of some instrument on D1 over the last 5 years, and you see that it is positive at a 10 day lag. Can you build a profitable strategy based on that? :D

No. So?

Don't you have enough skills to put QC anywhere else except ACF? And QC between instruments? No? Can't you think of it?