Linear regression channel - page 3
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 can a variable be a straight line?
Please express yourself correctly.
Really don't get it, or are you looking for something to get at?
Pearson, indeed, is easily accelerated. But not the width of the LR channel, unfortunately.
I'm not just talking about acceleration, I'm talking about getting rid of cycles altogether.
And the width of the HR channel can be calculated differently. If you mean maximum and minimum, then yes - this is another case where the cycle is essential.Really don't get it, or are you looking for something to get at?
And even without the x*y summation loop? What if x and y are not straight lines?
OK. Answer.
And even without x*y summation cycles
I don't just mean acceleration, I mean getting rid of cycles altogether.
Yes, that's exactly what I meant by acceleration. Pearson does this.
Rather, we should define the width of the LR channel using bar closing prices as an example.
The only input parameter for such a LR is how many bars are counted.
A single pass on each new bar calculates the midpoint line of the channel.
The channel width for each line is the RMS of prices from the middle line.
Therefore, it is not at all clear how a new RMS can be obtained quickly if all the summands in the new RMS are different from the previous one?
OK. Response.
And even without x*y summation cycles
I can allow for this. Only in this case, if neither x nor y are straight lines, there will be no speed gain. It's just that the 'along' loop would change to a 'across' loop.
So it is not at all clear how a new RMS can be obtained quickly if all the summands in the new RMS are different from the previous one?
You can. I can't say that I solved this problem quickly, but I did. I had to write several pages of formulas.
...
So it is not at all clear how one can quickly get a new RMS when getting a new line, if all the summands in the new RMS are different from the previous one?
It is possible to quickly obtain a line similar to RMS, but the real RMS is not.
You can. I can't say I solved it quickly, but I did. I had to write several pages of formulas.
Don't assume that the whole world is dumber than you.
I can allow for this. Only in this case, if neither x nor y are straight lines, there will be no speed gain. It's just that the "along" cycle will change to a "across" cycle.
Sir, you're just being facetious. ))
Sir, you're just being facetious. ))
What else is there to do with such statements?
It's not a joke about changing "along" to "across". It is a figurative representation of the way calculations are done.
In one case, you have to go through the data in a loop, and in the other case, you have to go through an array of intermediate values of the same length.