The Sultonov Regression Model (SRM) - claiming to be a mathematical model of the market. - page 9
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
Where do we find a quotient with a normally distributed residual? We can only make it up, but we don't consider that case here.
Residuals are the difference between the predicted value and the real value. Here you are calculating the error - in fact you are analyzing the residuals. But you are counting the cumulative residuals and you have to look at the whole distribution.
Where do we find a quotient with a normally distributed residual? We can only make it up, but we don't consider that case here.
That's a mistake. If we smooth with a straight line, it will be non-stationary, but if it is 18? In any case, in HP smoothing the residual is very often stationary (not always).
Well, to be more precise, the leftovers are still normal)))
At first, to keep the sheep safe and the wolves well, let's take this postulate as an axiom and forget about the problem temporarily, there is no other way out. We are facing a non-stationary, abnormal, non-deterministic, ...., unidentified market. Let us approach it by its own methods.
Are you referring to the poke method?
No, it's normal.
Normal is a point and stationary is a process. By making these distinctions I get a dynamic.
Now I can't remember the remainder being tested for normality, but the unit root test thrives.
That's not a good idea. If you smooth out a straight line, it will be unsteady, but if you smooth out 18? In any case, when smoothing HP, very often the residual is stationary (not always).
At first, to keep the sheep safe and the wolves well, let's take this postulate as an axiom and forget about the problem temporarily, there is no other way out. We are facing a non-stationary, abnormal, non-deterministic, ...., unidentified market. Let us approach it by its own methods.
Naturally.
Are you suggesting the poke method?
If smoothed using (18), it will not be possible for the system to reject this technique due to repeated use of the same pattern, but it is worth a try.
18 is an analytical formula. We calculate the function values using it and take the difference with the quotient. We obtain the smoothing error. Let us start working with this error. Or did I miss something?
Normal is a point and stationary is a process. By making these distinctions I get a dynamic.
I can't remember now that the residual is tested for normality, but the unit root test thrives.
If the chosen regression model describes the true dependence well, then the residuals should be independent normally distributed random variables with zero mean, and there should be no trend in their values.
What kind of stationarity is there?
P.S. Been to the mammoths, come back, back with you...