Not the Grail, just a regular one - Bablokos!!! - page 66
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, it is clear that we are talking about perfect stationarity there. When we are talking about temporal (which is closer to reality), or as it is called quasi-stationarity, then the sample average makes sense.
We know from cointegration theory that there are many cointegration vectors which I think will generate different residuals from a cointegration regression. Among these residuals, the most interesting ones are those that have maximum deviations from the mean, which in theory should increase returns for the same level of risk.
But how to approach this problem, I do not know.
If we managed to find all or at least some of these cointegrating vectors, we could at least try to find if not the optimal one, at least the best one.
We know from cointegration theory that there are many cointegration vectors which I think will generate different residuals from a cointegration regression. Among these residuals, the most interesting ones are those that have maximum deviations from the mean, which in theory should increase returns for the same level of risk.
But how to approach this problem, I do not know.
If I could find all or at least some of these cointegration vectors, then I could at least try to find if not the optimal one, then at least a better one.
Try Kohonen to select these mods on recent history. It should work.
Try Kohonen to pick out these mods on recent history. It should work.
We are talking about cointegration vectors.
I've got
Is there a database somewhere with indicators and other scripts for dealing with spreads?
If not, can someone start one?
There is a modest set available here:
http://www.procapital.ru/showthread.php?t=28081 (1 post - glossary)
https://www.mql5.com/ru/code/10096 - I still haven't got into the workings of this very promising group of indicators! I start to try it and stop thinking! I cannot get it to work... Can someone "write" a detailed step-by-step "manual"?
https://www.mql5.com/ru/code/10096 - I still haven't understood how this very promising group of indicators works! I start trying it and stop thinking! I can't get it to work... Can someone "write" a detailed step-by-step manual?
Not by this author.
There is a modest set available here:
http://www.procapital.ru/showthread.php?t=28081 (1 post - glossary)
https://www.mql5.com/ru/code/10096 - I still haven't got into the workings of this very promising group of indicators! I start to try it and stop thinking! I cannot get it to work... Can someone "write" a detailed step-by-step "manual"?
Not this author.
What's wrong?
It doesn't matter, you can read all his posts for the sake of curiosity