create an expert for mt4 using a programme made in exel - page 28
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Yes Fourier in no form is intended for extrapolation. What do you want to find in RMS if the function to be approximated is supposed to be periodic? What's the point of the RMS, then? Take the appropriate values from the beginning of the interval ......
Good luck.
Quite right, I have always asserted that expansion into series of functions is a pernicious method, where terms of a series initially have no physical sense, there is an attempt to hide one's inability to truly search laws - Taylor and Fourier indulged, competing with contemporaries and showing the power of their minds in questions of higher mathematics and they managed it, but far from recommending to apply these methods in similar situations.
But an Excel spreadshift would be a thrill to see...
;)
(c) to the founder of 123.
Thanks to him and the accountants we came up with 512K
Quite right, I have always maintained, decomposition into a series of functions is a pernicious technique, where the terms of the series are inherently devoid of physical meaning, is an attempt to hide one's inability to truly search for patterns
Uncle! I'm going to bed - but you're certainly on your "destructive to immature minds" wavelength.
And the criterion for a ban is simple - a lack of response to questions that are negative for "theory".
At the same time, the questions are simple and understandable to most
You know - I would also wish you better luck.
I personally have experience in predicting real processes after extracting significant harmonics.
And your failures are not a basis for hasty conclusions.
;)
market price is not a harmonic, but a scarier thing
market price is not a harmonica but a scarier thing
Scary already!
Névzhe crocodile?
I'm only talking about approximation so far. OOS is a different story, it's much more complicated and the main issue is the adequacy of the model. But if you compare sine waves without damping and with damping, the latter have more potential.
Every process has its own pattern, not some kind of sinusoid
The main one is the power of the spectrum, I see. But it was simpler there - there were several data series. Periodicities occurring during one process definitely had an effect and caused a reaction and reflection in the other. The length of time series for forecasting was short. But by pointing out the frequencies on long series and after checking their consistency on short ones, the result was successful.
It was a long time ago... 82 of the last millennium.
;)
The question of finding a satisfactory sample, I confess, has not been solved for me either, in this I ask for help, while the robot chooses from all the possible options the best, from its point of view
Every process has its own inherent regularity, not some kind of sine wave.
I will listen - with bated breath.
The law is for everyone!
And that's right - with measure.
If you're 100-one res...
but I will not interrupt the Guru.
Hodja Yusuf!
could you decipher this thesis a little more?
If there is a process, and there is an inherent pattern to it - is there no right solution other than Gamma functions - what will be in a moment?
2 yosuf:
maybe you are looking for this script: https://www.mql5.com/ru/code/8175?
ZS: tired of googling Yusufhoja's posts in parts on the net, pretty much the same as here - incomprehensible predictions and squabbles ;)
No need to look for my posts - here I am in front of you
The conclusions are not based on failures, but on an analysis of the basics of the Fourier series expansion method. This expansion has a limitation: it can only represent a function that is periodic on the expansion segment. Accordingly, if a Fourier expansion is used, the function is assumed to be periodic, strictly f(x) = f(x+T), where T is the period. I hope you do not need to tell what value of the function you get when you try to extrapolate beyond the expansion segment for a periodic function? If done correctly and taken an infinite number of harmonics, then the corresponding from the beginning of the interval. If a finite number of harmonics, then accurate to the approximation error. The OOS is simply selecting the appropriate values from the beginning of the decomposition range ;) .....
Good luck.
ZY about real processes: they are predicted if there is a periodic component, e.g. cyclic load or carrier frequency, which, IMHO, we don't see in the market. The method itself is quite popular not only in radio engineering, but was popular in mechanics - it's easy to count integrals by hand (I counted in my time ;) ), with development of methods of numerical integration for mechanics the relevance is reduced......
You are quite right, glad for such reasoning