Obtaining a stationary BP from a price BP - page 5
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
How a non-stationary market can be turned into a stationary market is unclear.
Actually, one should distinguish between the spectrum of a deterministic signal and the power spectral density of a random process.
>> so ..... ? So what? Spectral power density is not useful for traders because it doesn't allow to predict (synthesize) the FORM of a signal in the future. And 80% of all writings are devoted to this very "spectral density". It works in physics, in optics FOR ANALYSIS. But traders for extrapolation need SYNTHESIS after ANALYSIS, and it needs accurate synthesis. Therefore, if traders need a "spectrum", it should be for a "deterministic", i.e. non-random signal.... THIS (a sinusoidal spectrum) does NOT exist in time series. This is why Fourier analysis does not work in trading with ANY degree of accuracy.
Actually, one should distinguish between the spectrum of a deterministic signal and the spectral power density of a random process.
Recall the topic: not before deterministic signals. The question is simple: open the attache to my post and visually try to convert all this dancing to a stationary process. For me it is obvious that we should forget about such transformation and deal with non-stationary process. SPM, unlike probabilistic exercises, also has a phase. What happens to the parameters of the non-stationary signal (and which ones), before the changes in the trends?
The topic has scaled up again.
How a non-stationary market can be turned into a stationary market, I don't understand.
This forum is full of such understanders - they want it all and have been chewing on this nonsense for several years.
So ..... ? So? Spectral power density is not necessary for traders, because it does not allow predicting (synthesizing) the shape of the signal for the future. And 80% of all writings are devoted to this very "spectral density". It works in physics, in optics FOR ANALYSIS. But traders for extrapolation need SYNTHESIS after ANALYSIS, and it needs accurate synthesis. Therefore, if traders need a "spectrum", it should be for a "deterministic", i.e. non-random signal.... THIS (a sinusoidal spectrum) does NOT exist in time series. That's why Fourier analysis doesn't work in trading with ANY degree of accuracy.
naturally. SPM is a probabilistic characterisation of a process.
Reshetov, you still don't understand what we are talking about. No one suggested taking any noise as a model. I'm too lazy to repeat the same thing.
Recall the topic: not before deterministic signals. The question is simple: open the attache to my post and visually try to convert all this dancing to a stationary process. For me it is obvious that we should forget about such transformation and deal with non-stationary process. SPM, unlike probabilistic exercises, also has a phase. What happens to the parameters of the non-stationary signal (and which ones), before the changes in the trends?
Well, for example, it can be noticed, that the weighted average of FFT signal (if to speak conventionally about a spectrum of concrete SP realization) slips a little to the high frequencies...
Recall the topic: not before deterministic signals. The question is simple: open the attache to my post and visually try to convert all this dancing to a stationary process. For me it is obvious that we should forget about such transformation and deal with non-stationary process. SPM, unlike probabilistic exercises, also has a phase. What happens to the parameters of the non-stationary signal (and which ones), before changes in trends?
And doesn't your model involve reducing to stationarity on a variable time window and finding the parameters of those stationary distributions? If you have something to say and discuss on the subject why don't you start a branch?