![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
>> ...which once again points in Laplace's favour.
You got it, you tongue-tied devil :)
You got it, you tongue-tied devil :)I'm already having second thoughts myself....
I don't use distribution returns to assess risk. I think it is more correct to model sequences of trades - if possible.
I'm already having second thoughts myself....
It now seems to me that pricing is a generalised Poisson process, which is non-stationary in intensity on short intervals, but on larger intervals - where we estimate statistics - its average value is quite smooth. Hence, the distribution graph should be a curve (L^k)/k!*exp(-L), where L is the intensity.
P.S. You stop me if you get carried away...
It now seems to me that pricing is a generalised Poisson process, which is non-stationary in intensity over short intervals, but over large intervals - where we estimate statistics - its average is quite smooth. Hence, the distribution graph should be a curve (L^k)/k!*exp(-L), where L is the intensity.
P.S. You stop me if you get carried away...
I think so too. This is where the most reliable filter comes in - the integration of a random variable. And we have a stationary series or so on the days.
I think so too. Here the most reliable filter is activated - the integration of a random variable. And we have a stationary series on the days, or so it seems.Yeah. What especially inclines me to this idea is that the sum of Poisson processes is also a Poisson process, so the shape of the curve on, say, hours, four-hours, and daily periods should be the same, which is generally confirmed by the experiment. The only confusion is the requirement of independence of the increments - and they are known to be a function of the so-called "market mood" to some extent.
Yeah. What especially inclines me to this idea is that the sum of Poisson processes is also a Poisson process, so the shape of the curve on, say, hours, four-hours, and daily periods should be the same, which is generally confirmed by the experiment. The only confusion is the requirement of independence of the increments - and they are known to be a function of the so-called "market mood" to some extent.
Yes. It is necessary to call Reshetov, it is interesting what he will tell. :)
Yeah. We should call Reshetov, I wonder what he's gonna say. :)>> I wish there was a "call so-and-so" button.)
Yes. It is necessary to call Reshetov, it is interesting what he will tell. :)I won't say anything, except that the discussion is nerdy blather, and I'm not interested as it has little or nothing to do with applied trading.
Ordinary rubbish of nerds: who will use more scientific terms in fludder, he is cooler.