Forget random quotes - page 51

 
Why then do you refer to nonexistent evidence, fictitious facts and other scholasticism? It is obvious that your econometrics cannot distinguish one state from another, it makes no difference whether you work with random GARCH or a real market, all its statistics, all its methods, all its conclusions can just as well be applied to a roulette wheel.
 
faa1947:

No, this is the first stage of the analysis. If there is a deterministic component in the series, the statistics reacts only to it and everything else can be ignored.

After determining, we do the analysis further. The result in the form of TS, of course, includes the selected trend.


Econometrics is simply a set of tools that we need to be able to apply. It is useless to take a time series outright and calculate something without pre-processing it, detrending, etc. - is useless. You need to know where to look - i.e. filter the bazaar.) Once that's done, you can go on and get wise to it. Only then you can make do with simpler tools
 
Avals:

Econometrics is simply a set of tools that you need to be able to apply. It is useless to take a time series and calculate something without pre-processing it, detrending, etc. - is useless. You need to know where to look - i.e. filter the bazaar.) Once that's done, you can go on and get wise to it. Only then you can get by with simpler tools .
+1
 
Avals:

Econometrics is simply a set of tools that must be able to be applied. This means that it is impossible to simply take time-series without their pre-processing and calculate something, detrending and so on. - is useless. You need to know where to look - i.e. filter the bazaar.) Once that's done, you can go on and get wise to it. Only then you can make do with simpler tools

I'm sitting here wondering why I keep agreeing with you.

I would add the aphorism of Box and Jenkins: "There are no right models - only useful ones". And my experience shows that the more "correct" the model, the more useless it is. And the qualification consists not just in the knowledge of the tools and methods, but the ability to select from these tools and methods a certain minimum of the tools and methods, which will be sufficient for a stable and profitable trade.

 
faa1947:


To add to this, Box and Jenkins' aphorism: "There are no right models - only useful ones".

In fact, they are lying, because there are also useless ones.
 
faa1947:

Dear traders!

I mentioned above and it can be checked that 368 people downloaded the R wrapper and 582 people downloaded the example. It means that for these hundreds of people there is no problem of selecting and identifying the trend, because they know many ways to do it, they know the appropriate programming code, they use it in practice and they know the advantages and disadvantages of each method. In you google it and you don't find it! Of course, within the confines of this thread and this forum, your posts are on point. But from the point of view of the hundreds of people mentioned, your posts are mere flubber. Such is the uncovered, naked truth of life.

This does NOT mean that "for those hundreds of people, there is no problem highlighting and identifying a trend"!!! It means just the opposite -- that the problem was, is and is not going anywhere.

It just means you're wishful thinking. Well, you wish too much ;))))

But of course, the "traders" can neither understand nor accept "such an uncovered, naked truth of life" -- that's why they deserve such an affectionate and disparaging treatment from your econometric lips, eh?

 
avtomat:

This does NOT mean that "for these hundreds of people there is no problem of highlighting and identifying a trend"!!! It means just the opposite - that the problem was, is and is not going anywhere.

And it just means that you are wishful thinking. You wish too much ;))))


There's no problem with detrending. Lots of qualitatively different methods. The most elaborate tool.

Don't tell me what I have and don't have.

 
You're doing bollocks again, lots of clever words - zero output, correlation, determinism - it's all total bollocks guys.
 
Let them have their own hemispheres, is that a pity?
 
faa1947: I will add to this the aphorism of Box and Jenkins: "There are no correct models - only useful ones".

It's not their aphorism. Once I needed systems theory, I studied it.

There it is almost an axiom: "The question of model correctness in systems theory is incorrect, because the very structure of the model is determined by the subjective division of the system into object of influence and environment".