How do you properly compare two non-overlapping rows? - page 2

New comment
 
Dmytryi Nazarchuk:

Time series standardisation - all statistical packages have it

Can you give us an example?

 
Evgeniy Chumakov:


There are two non-overlapping rows that are on 'different levels' (like in the picture above).

How can they be 'combined' so that they are side by side and overlap?

You could use price logarithm.

 
Renat Akhtyamov:

Can I have an example?

Can

 
CHINGIZ MUSTAFAEV:

Bring the beginnings of the two graphs to zero.


Off-topic. There is no beginning of the rows (in the full sense), the beginning is sort of at the point where the calculation starts. Why advise such a thing?

 
Vladimir M.:

Why combine them? What difference does it make which graphs take the data in the first place? You will still be using arrays of data. For example:

https://www.mql5.com/ru/docs/standardlibrary/mathematics/stat/mathsubfunctions/statmathcorrelationpearson

I didn't ask about correlation. It's no good.

 
Renat Akhtyamov:

then they will go their separate ways and will not cross paths in the near future

And why is that? I'm just not that good at it, but it's interesting to understand.
 
Evgeniy Chumakov:


Off-topic. There is no beginning of rows (in the full sense), the beginning is sort of at the point where the calculation starts. Why advise such a thing?

So it is useless, there will always be relativity of readings, so there will be an error that cannot even be identified.
And if you can identify it, then you can solve it, a vicious circle.
And when this is the case, the only option is probably incremental.
But my opinion is probably wrong.
 
CHINGIZ MUSTAFAEV:
So it's all useless, the relativity of the readings will always be there.


I agree. Everything will vary from sample size and will be relative.

 
Dmytryi Nazarchuk:

Can

What's the scale on the left? What is it?
 
Dmytryi Nazarchuk:

Can we go to

Thank you, that's understandable.

title or link if you don't mind?

123456789
New comment