The Sultonov Regression Model (SRM) - claiming to be a mathematical model of the market. - page 11
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
It is possible to try this. Here is an indicator that implements (18), maybe the programmers can carry out this operation?
I have installed it, I don't understand anything. Where is the smoothing? Or there is no smoothing at all?
Well, then a regression model would be a dead giveaway. There are a lot of experts who know regression analysis, but only a few are making money in the market.
Regression is a starting point. The next step is ARCH. Then the next ....
a model without residuals is a model that predicts series values without error. The residuals are the error (the difference between the predicted value and the real value). So there is actually a decomposition into a deterministic component (forecast model) + noise (normally distributed residuals)
That row contains 45 zeros and 45 ones. The expectation is 0.5.
It doesn't understand binary patterns. We need something simpler.
Yes, of course. But the residual is tested by the unit root test, which is stationarity.
Another problem. What if it is not exactly as you have written? And if it is as you have written, can the prognosis be trusted?
No, the residuals are tested for normal distribution (z-test for example). Stationarity is probably tested for something else))
I disagree. The "deterministic" or "average" is also shaped by noise. There is a vicious circle here: in order to predict, one must know the results of the prediction, it turns out. Something has to be renounced. Otherwise it is a dead end.
There is no deadlock. Avals is fine - he hasn't lost a bit of information: add the deterministic with the remainder and you get the original quotient.
How do you explain the fact that the RMS has raised the MO to 0.8787? Moreover, if the RMS input is strictly alternating between 0 and 1, it also shows 0.5. So, there is a circumstance in the series you have given which shifts this equilibrium towards 1.
You don't need to look for the magnitude of the error, you need to analyse its distributions. For simplicity, you can simply construct this distribution visually
There is no deadlock. Avals is fine - he hasn't lost a bit of information: add the deterministic with the remainder - you get the original quotient.
I disagree. The "deterministic" or "average" is also shaped by noise. There is a vicious circle here: to predict, one must know the results of the prediction, it turns out. Something has to be renounced. Otherwise it is a dead end.
The question is not about how and on what to base the forecast, but how to check its validity. If the residuals (error) are not Gaussian distributed, it's no good))
you do not need to look for the magnitude of the error, you need to analyse its distribution. For simplicity, you can simply plot this distribution visually