FIR filter with minimum phase - page 2
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
Back to the subject.
What's in this MA for you? At least give me a hint, what do you want to do with it?
I'm not being facetious. I'm really curious. Maybe I'm missing something...
Возвращаясь к сабжу.
What do you want with this MA? Give me a hint, what do you want to do with it?
I'm not being facetious. I'm really curious. Maybe I'm missing something...
OK, I'll describe it from the beginning. First of all, it's not MA, it's a bandpass filter. What's it for? To build something like this:
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art7_i17.pdf
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art4_i18.pdf
it's described very smoothly but what about the lag?
Right. Sorry - not interested. It's schizo. IMHO, of course.
Otherwise, yes - who's stopping it. It's a fun experiment in common sense - can we play for money?!
Peter_Zabriski:
OK, I'll describe it from the beginning. First of all, it's not MA, it's a bandpass filter. What's it for? To build something like this:
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art7_i17.pdf
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art4_i18.pdf
It's described very smoothly, but what about the lag?
Peter_Zabriski:
OK, I'll describe it from the beginning. First of all, it's not MA, it's a bandpass filter. What's it for? To build something like this:
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art7_i17.pdf
https://www.mql4.com/go?http://belisa.org.by/pdf/Publ/Art4_i18.pdf
It's all very well described, but what about lag?
Don't be fooled. If you can master Matlab, you can master specialized packages for measuring economic data - econometrics, such as EViews, R. There are tons of them.
In econometrics, the issue of filters is a small part of the problems that have to be solved. In econometrics, filters are one kind of smoothing tool and not the most used. There are also regressions in an awful variety, wavelets, splines. But solving the smoothing problem is the very beginning of problem solving and the easiest. and when you start solving the remaining problems after smoothing, you won't care about lags.
In econometrics you will see what economic data decomposition is, not that childish babble in the link.
When it comes to decomposition, the most primitive, most complete and with an extremely atomic level of simplification is PF.
I.e. use not one filter, but several with zero overlap. For example: 1-3, 3-5, 5-8, 8-13.... In this way, the phase will be compensated.
Prerequisite, all filters must be of the same type and order.
Right. Sorry - not interested. Schizo. IMHO, of course.
Otherwise, yes - who's stopping it. It's a fun experiment on common sense - why don't we play for money?!
Don't be fooled. If you were able to master Matlab, you can master specialized packages for measuring economic data - econometrics, such as EViews, R. There are tons of them.
In econometrics, the issue of filters is a small part of the problems that have to be solved. In econometrics, filters are one kind of smoothing tool and not the most used. There are also regressions in an awful variety, wavelets, splines. But solving the smoothing problem is the very beginning of problem solving and the easiest. and when you start solving the remaining problems after smoothing, you won't care about lags.
In econometrics you will see what economic data decomposition is, not that childish babble in the link.
Thanks for participating in the discussion, but unfortunately good advice can only work if one is mature
When it comes to decomposition, the most primitive, most complete and with an extremely atomic level of simplification is PF.
I.e. use not one filter but several with zero overlap. For example: 1-3, 3-5, 5-8, 8-13.... In this way, the phase will be compensated.
Prerequisite, all filters must be of the same type and order.
Yes it's about decomposition, but not linear scale of frequencies, but logarithmic one, like here
http://kit-e.ru/articles/plis/2008_09_131.php, is PF referring to the Fourier transform?
In case you're not aware, the evil Renat banned me, the good Swinosaurs. (No way, boss!)