Linear regression channel - page 16
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
ZZZI and not to bother with flooding, let's agree that you in turn give your word not to pick on Dmitri first, and keep it - there will be respect for the word.
In return for what? I do not give a shit about it, as long as he does not start running around on technical topics, especially relating to the pros, talk nonsense and troll members, mentioning "club" and other nonsense.
It's just that in this thread his trolling was beautifully translated into self-banning, which I thanked him for.
no of course. If this point lies on the MA of the same period as the regression channel, then it is generally calculated from the left half of the channel data and the same size data to the left of the channel range. How can it coincide if the calculated data are different?
Nikolay,fxsaber is absolutely right. There is no point in arguing.
The regular MA is the same as a zero-degree polynomial, but not the first-degree polynomial.
A polynomial of degree zero:
y=a;
First degree polynomial:
y=ax+b;
Any regression function should match the MA if it is calculated correctly, not just any polynomial. The URM https://www.mql5.com/ru/articles/250 is also exactly the same as the MA.
The width of the channel needs to be determined, unambiguously, only as follows:
top line: y=a+bx +CKO;
middle line: y=a+bx
bottom line: y=a+bx -CKO;
In the general case:
top line: y=a+f(x) +CKO;
middle line: y=a+f(x);
bottom line: y=a+f(x) -CKO;
There was a suggestion to download the demo and make sure that the channel width equals sko multiplied by 1.41. I downloaded, checked, it turned out not to be so.
Why the mysterious 1.41? I assume it's the root of two. What does that have to do with a two?
I don't understand this programming stuff - where to attach recursion, which function to inline... and I don't see any point in such a regression showing the past at all
Show me a regression outside of the past.
Nikolai,There is no point in arguing.
Why is that?
On the contrary, arguing is very useful, especially with fxsaber.
Why not?
On the contrary, it is very useful to argue, especially with fxsaber.
NNikolai, it follows from the definition of a regression channel that the channel is constructed by equidistant lines distanced by the RMS value from the mean line constructed from the actual data of the selected period. There is no other way. More noise from nothing.
NNikolai, it follows from the definition of a regression channel that the channel is constructed by equidistant lines distanced by the RMS value from the mean line constructed from the actual data of the selected period. There is no other way. More noise from nothing.
The noise was not at all on this obviousness.
The noise was about the possibility of calculating RMS without a single cycle (except for the first calculation).
Yusuf, please read this thread with diligence, not diagonally, if you want to insert comments.
SZY, today is exactly a month since Fedoseyev has self-imposed himself off the forum for a month. Kudos to him for keeping his word.
The noise was not at all about this obviousness.
The noise was about the possibility of calculating RMS without a single cycle (except for the first calculation).
Yusuf, please read this thread with diligence, not diagonally, if you want to insert comments.
SZY, today is exactly a month since Fedoseyev has self-imposed himself off the forum for a month. Kudos to him for keeping his word.
How did you manage to do without cycles? After all, when a new bar arrives, you must include it in the calculations, and remove the data of the oldest bar from the sample and repeat the whole cycle of calculations. How else could it be?
Why did Fedoseev self-delete, reasoning correctly?