Econometrics: why co-integration is needed - page 6
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
Can you show the cointegrated instruments? So that the difference is stationary.
No, not all of them. I'm not going to teach.
I agree, I mean linear correlation - anticipating your answer to the previous question
San Sanych!
Can't be trusted, but can be trusted with that probability :)
I don't understand anything. I will read what false correlations are.
I think what faaaa meant was that if his fridge defrosts by itself every 28 days, then this event correlates with the phases of the moon with a coefficient close to 1.00, but that does not mean that the phases of the moon depend on the rhythm of defrosting his fridge (correlation is not a relationship).
OK, let's put it another way. I'm ready to send you an EA that emulates primitive trend trading tactics. It does not lose money because it does not take into account commissions, gaps and slippages. It opens a position in the moment when the trend is detected, and closes it when it is broken. In short, it is a simple trend-following Expert Advisor. Are you ready to study it from the econometric point of view?
Can you show cointegrated instruments? So that the difference is stationary.
Read my first post in this thread.
Co-integration is a very powerful concept. Two random processes are considered to be co-integrated if the difference between them is a stationary random process. Trends and biases, if present in random processes, must be removed.
Dear Econometrician, read the definition I gave earlier.
Read, after all, wikipedia, which says in normal language that "Before the 1980s many economists used linear regressions on (de-trended[citation needed]) non-stationary time series data, which Nobel laureate Clive Granger[1] and others showed to be a dangerous approach that could produce spurious correlation."
I wonder if cotier and profit are cointegrated or not?
If they are not cointegrated, then the profit is random. And if they are cointegrated, then the profit is not random?
If someone gives me a file with two rows: kotir and profit, then I will count the cointegration. Very curious.
Co-integrated in the case of a buy-and-hold strategy. Not cointegrated in the general case, although it is possible to construct examples of profit series where this cointegration would be the case.
There's no connection with the randomness and non-randomness of the profit here at all.
faa, at least explain something on your fingers. Well, say, false correlation.
http://www.burns.com/wcbspurcorl.htm
But now I have and can prove that I have cointegration. So what?
Well try proving out-of-sample. I'll give you a clue as to the mistakes...
If I have specifically, the dollar index was taken and compared to the eurodollar pair. This shows the economic basis for the existence of cointegration between these series.
Where is this index traded? Or at least futures on it? Now your results are a proof that for any series you can construct another one, and this pair of series will be cointegrated.
If you read about cointegration, the trend issue is fundamental.
Believe me, I have read and (unlike you) have a practical idea of how to apply it. I've even written for what and how cointegration is applied.
There is always the issue of false correlation when using a multicurrency. It just seemed to me that cointegration is a tool to cut out false correlation.
Co-integration and correlation are different concepts altogether. One can exist without the other, and in no way does either concept entail the existence of the other.
Conclusion: it doesn't fit, so they don't depend.
Then you've chosen the wrong model. Use a non-linear model, such as polynomial regression, and you'll be happy.
I will disappoint you with the following fact. Fitting has nothing to do with the independence of random variables. There is a strict definition of independence in the theorist.
That's how the topic started. That's the point. Take a look, with graphs and calculations. But what to do with it?
OK, let's put it another way. I'm ready to send you an EA that emulates primitive trend trading tactics. It does not lose money because it does not take into account commissions, gaps and slippages. It opens a position in the moment when the trend is detected, and closes it when it is broken. In short, it is a simple trend-following Expert Advisor. Are you ready to study it econometrically?
I am interested in quotes and balance values of your Expert Advisor at equal periods of time. In the form of /csv. I myself am interested to see the cointegration between the two series. Apparently not everyone has understood the importance of success in this case. In addition to the forward test we will get a more reliable tool.
Click on the file. I will calculate it tomorrow.