Regression equation - page 12

New comment
 
Prival:


if there's anything else like it. please share the links. I've been poking around in this particular area for a long time. it's interesting

Fundamentals of Information and Signal Transmission Theory

Mathematical modelling and national economic research

Information theory. A selection of books.

 

Yep, it's all very useful.

As promised, picture. Performed analysis of pure price series (no preprocessing, trend removal etc) - AR(3) model on 11 counts. On the charts - prediction error: upper chart - for ANC, lower - quantile regression. Lines: blue - Close, green - High, red - Low (median and quantiles 0.9 and 0.1 were taken for QR, respectively). Blue lines are daily APR, for scale.


What I see here is the following:

(a) Absolute values of the error for the ANC in a calm market are almost the same as for QR, but(!) when a spike appears the ANC error changes more chaotically and generally reacts to it more weakly, while the second chart error looks more regular. This, in general, was the goal: to show the possibility of detecting "stationarity disruptions" at the expense of QR's ability not to react to these very spikes. And if they can be detected, it means that it is not outliers but additive random process, and not less stationary than the AP(3) from which we separated it.

b) if we consider outlier detection to be a useful signal, the second graph has many times more OSR, therefore a hypothetical :) trading system based on this effect will give as many times less false signals.

Of course, one can argue here, but here is what we get on M5 (AR(3), on 21 counts):


Here, already much more clearly.

In general, it seems to me that what I was saying is gradually confirmed. I will dig further in this direction.

I am attaching the library for QR calculation (compiled Gallant library, see link two pages before) and the header file with description. I don't attach indicators themselves, I can't separate them from the rest:))) but there is nothing difficult, the formula is already written

Files:
qr.rar  22 kb
 
What the hell happened to the pictures?
 
alsu:

(a) Absolute error values for MOC in a calm market are almost the same as for QR, but(!) when a spike appears the MOC error changes more chaotically and generally responds weaker, while the error of the second graph looks more regular. This, in general, was the goal: to show the possibility of detecting "stationarity disruptions" at the expense of QR's ability not to react to these very spikes. Since they can be detected, it means that they are not outliers but additive random processes, and not less stationary than the AP(3) from which we detached it.

This is a property of quantiles, in particular the median. I talked about this in relation to the median correlation coefficient.

Thanks for the work!

 
alsu:

Yep, it's all very useful.

As promised, picture. Performed analysis of pure price series (no preprocessing, trend removal etc) - AR(3) model on 11 counts. On the charts - prediction error: upper chart - for ANC, lower - quantile regression. Lines: blue - Close, green - High, red - Low (median and quantiles 0.9 and 0.1 were taken for QR, respectively). Blue lines are daily APR, for scale.


No pictures are visible
 
Vinin:

I can't see the pictures
They open via a link, but don't appear that way for some reason (I don't know what's wrong)
 
hrenfx:
Stochastic analysis of complex dynamic systems. Market Fore
Well, well. The rate change process is assumed to be ergodic.
 
Mathemat:
Well, well. The process of course change is supposed to be ergodic.

My education is only high school (10th grade). Therefore, there is no knowledge to speculate about high matter.
 
Mathemat:
Well, well. The course change process is supposed to be ergodic.
So what if a dfmn from the Institute of Steel and Alloys publishes on "forex analysis" - that's a hint: ))))
1...5678910111213141516
New comment