For those who have (are) seriously engaged in co-movement analysis of financial instruments (> 2) - page 27
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
Well, wavelets are also a way of spectral analysis.
You have already found Fourier. What other ways are there?
Andrey, the man is not at all aware of spectral analysis and its variety. I wanted to enlighten him on the application of decomposition into harmonic components, where Fourier works are just one of many ways of decomposition. But I realized that he will not even pull selective filters, which have nothing to do with decomposition into harmonic components by Fourier decomposition and the like.
Let it self-decompose.
Spectral analysis is the basis of any research in any branch of science, engineering, linguistics and many other things... It is foolish to neglect it in market research and trading.
The horror of obscurantism...
And poncey.
Can I add about the "selective filters" for poncey?
And about the singularity of the transition matrix...
DDD
Don't embarrass yourself.
One minus the variance of the product of the original matrix (in the columns, the sample of FI prices, reduced to zero MO and RMS one) and the normalized (sum of squares of elements equals one) eigenvector corresponding to the minimum eigenvalue of the correlation matrix (obtained from the original).
P.S. The demonstration above shows about 80,000 such values in each frame, calculated for a daily sample.
One minus the variance of the product of the original matrix (columns sample FI prices reduced to zero MO and RMS one) and the normalised (sum of squares of elements equal to one) vector corresponding to the minimum eigenvalue of the correlation matrix (derived from the original).
The horror of obscurantism...
And poncey.
Can I add about the "selective filters" for poncey?
And about the singularity of the transition matrix...
DDD
Don't embarrass yourself.
In order not to look silly, read my articles in BL. I showed how to apply spectrum analysis to trading and market research using the AIASM complex in a popular form. There are a series of articles in it. I should add a couple more, but have no time.
What's that got to do with Fourier? You obviously don't know anything about spectral analysis.
Alividerci.
No need to chat further, much less litter in someone else's thread...
There is no need to communicate further ...
Agreed...
I think you should have a couple of instruments before you go for 3 or more pairs.
Here's my... Arbitrage. Equity lime at the bottom for 10 years in pips minus spread. This is in lieu of the single currency tester - for tuning.
By the way, I told you a long time ago that nobody has created a proper correlation indicator. It should work like this (in blue), i.e:
//correlation is negative - growth(or decline) of R and decline(or rise) of L
//correlation is positive - growth(or decline) of R and growth(or decline) of L
//correlation closer modulo to 1 - strong relation, linear dependence
//correlation closer modulo 0 - no relation
Here in context L is one pair and R is another.
Green and red - combined trades - charts of the pairs, and pink - equity of the trade
Explain what and why in your picture.
If possible, attach the source of the correlation indicator from the screenshot.