Zero sample correlation does not necessarily mean there is no linear relationship - page 58
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
Avals:
And in general, that they need to be predicted to make money - no one. Who says so?откуда следует, что эти моменты непредсказуемы? - я так предполагаю. Рад буду если вы покажете мне такой метод предсказания.
I won't show you, but I use it. The equity of this one is in the profile.
Slava, this is the 50th time you've shown me Equity in the last 2-3 years)))))
Where's the fresh one?
Slava, this is the 50th time you've shown me Equity in the last 2-3 years)))))
Where's the fresh one?
do you need it? I can put it in a private message if I really want to))
No, no, thanks. If you don't show me the method, then don't.
Well, then it's a matter of believing or not believing))
Then when you try to create a TS
You have already created more than one.
and understand what's what and why the spread, etc. do the following - widen the analyzed time horizon.
Expanded. The spread still has no unit root :)
And, moreover, the onset and the end of this interval cannot be predicted. Non-stationarity, you see, occurs.
You see, it doesn't come suddenly if you think with your head when pairing instruments. If the economic reason for cointegration changes (dividends started paying in different proportions or something else happened) - stop trading the pair.
I already have and more than one. - Of course I did!
Expanded. The spread still has no unit root :) - I don't see stationarity in the figure. Honestly, sorry.... I see spread turbulence in 2008 - 2009.
You see, it doesn't come suddenly if you think with your head by pairing instruments. If the economic reason for cointegration changes (dividends started paying in different proportions or something else happened) - we stop trading the pair. - I understand. But I also understand that this is all just thinking. I can argue like this forever, about everything in the world.
The economic reason for cointegration changes - that's you pleased))). If cointegration has been there and then suddenly disappears, then such series are non-integrated.
If a linear combination of two non-stationary series suddenly becomes non-stationary, then at best you will have to wait a very long time to get the necessary amount of statistics and build a new model on its basis. And that's only if, after the "breaking point", the two series will again CREATELY acquire the property of cointegration.
You didn't create such a TS.
Post the ones about the financial markets.
Write the same article, but better. It's all right to criticise..........
If the cointegration was there and then suddenly disappears, then such series are non-integrated.
OK, if we consider the series as a whole, yes. But we can talk about a piecewise constant vector of cointegration. For those two stocks it would be exactly that.
If a linear combination of two non-stationary series suddenly becomes non-stationary, then at best you will have to wait a very long time to get the right amount of statistics and build a new model on it.
No, because the convergence rate of hedge ratio estimation is proportional to N, not to sqrt(N) where N is the number of observations.
You didn't build such TCs.
You're a bad telepath :D
There could be a false correlation between the rate of hair growth on your head and the dynamics of continental plate movement.