Difference calculus, examples. - page 2
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
1. Yes. This filter is 400 years old with only written history: Descartes, Newton, Pascal, Taylor, Lagrange.
2. Coefficients are calculated. I think in the second year we were introduced to Lagrange and Taylor methods. There seem to be a lot of variants for calculating coefficients.
3. I drew one today. :)))))
Great, namesake) But it is always important to me to know the final goal, is it there?
Great, namesake) But it's always important for me to know the end goal, is there one?
:)))
Of course. Only I do not want to voice it, it is likely to change "as the play goes on. :)))
I think we will get to experts and optimization.
When you increase the sample to N=100, the 4th degree equation gives a strong scattering of the estimated price:
I've been looking at your research, it's interesting.
Unfortunately, I'm not sure I'm immersed enough in your topic to answer. :-(
I propose to collect indicators and experts on the difference calculus in this branch in the open source code.
If there will be interest, we will eventually gather or draw something useful. :)
I rewrote the indicator in a clearer variant as an example:
This is all a kind of regression, just like withYosuf.
Regression is a return to the past, while you have to move forward, into the future!
Have you tried to progress, but not to regress?
It's all a form of regression, just likeYosuf.
Regression is a return to the past, while you should be moving forward into the future!
Have you tried progression rather than regression?
I would say that interpolation is a"tracer" asNikolai Semko (Nikolay7ko) says, and not regression at all.
And by progression do you mean extrapolation according to strict laws (the 2nd degree polynomial based onthe "tracer"), or something else?
I would say that in interpolation it is"tracer" asNikolai Semko (Nikolay7ko) says, and not regression at all.
And progression do you call extrapolation according to strict laws (the 2nd degree polynomial on the basis of"tracer" is given), or something else?
I don't know that one.
Interpolation and extrapolation = it's all regression.
Try to make the future yourself without looking back.
I don't know about that.
Interpolation and extrapolation = all regression.
Try making the future yourself without looking back.
:)))))
I thought we agreed, no philosophy.
P/S. There is a code, where is the regression?
I would say that in interpolation it is"tracer" asNikolai Semko (Nikolay7ko) says, and not regression at all.
And you call progression as extrapolation according to strict laws (the 2nd degree polynomial on the basis of"tracer" is given), or something else?
I don't remember saying that. I saidso and so.
I don't remember saying that. I saidso and so.
Forum on trading, automated trading systems and trading strategies testing
Spectral analysis
Nikolai Semko, 2017.11.05 04:28
From any redrawable indicator you can make a non-drawable indicator. Just form its tracing trace. But then the picture will be completely different. The only problem might be to create a fast tracer shaping algorithm. Personally, I managed to do it with polynomial decomposition. I have tried to form tracer using Fourier decomposition (just a spectral decomposition), but the tracer algorithm was very slow and the tracer itself was very "jumpy" due to peculiarities of this method (Fourier) approximation. And therefore hardly worthy of attention. The polymial tracer, on the other hand, gives fantastic results and overlaps all existing moving averages, if possible.
To make this clear, I made an animated GIF:
That's not what I meant. I didn't say that"in interpolation it's 'tracer trail' and not regressions at all."
Honestly, I don't even understand the meaning of that phrase.
I meant that all types of interpolation (it's more correct to say approximation) are redrawable (and your version is redrawable too). And only the tracing trace of these interpolation functions is not redrawable, which I supported my words with animated gifs. I advise to study them again carefully. In these gifs, the tracing trace is a two-color blue-violet line. But it is not an interpolation function. The blue color means that the interpolation function at this point is upward, and the purple one is downward.
If the polynomial degree is 0, this trace is a Moving Avarage