The St Petersburg phenomenon. The paradoxes of probability theory. - page 12
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
Naturally, from a single realisation of a random process (our price series) we cannot establish its exact form. This statistic will only allow us to determine the probability of being wrong, assuming the process is other than a random walk (a Wiener process). If this probability is less than the threshold we set - we assume the process is distinct from a random walk - this is the standard matstat approach. The distinction from a random walk is of interest to us because the distinction is a necessary (though not sufficient) condition for tradeability.
That's not what I mean. Trading is done on a very small finite sample, and this sample, with a probability of about one, itself has nothing to do with the distribution and can behave as it pleases. The advantage on a large sample of such trades nobody cares or can care about. For a working TS a significant advantage is needed already on 3-4 trades.
I.e. it is impossible to builda real TS on statistical regularities.
A new paradox can be formulated: the closer to the statistics the further away from the profits
No, you're wrong. Statistics can give us a clue, a working hypothesis, but not the answer itself. It is not certain that this key will fit the lock.)
I don't think they are for sale at all. You need a cow like that yourself.)
And it's almost certain that such TCs are not made on MKL.
you can sell them and not trade anymore, the one time incam will be many times more than the annual income from the trade
on MCL you can do anything and even moreBoth statements are true
But given that each subsequent (working of course) TC is better than the previous one, you can ignore the first post, provided that the TC is more than one.
No, you're wrong. Statistics can give us a clue, a working hypothesis, but not the answer itself. It's not certain that this key will fit the lock.)
Anyway, I'm removing the python and putting R again, just for the sake of statistics :D
I'm going to remove Python and put it back on R, just for the sake of statistics :D
Python, in terms of statistics, is much more interesting and better than R, and, imho, much easier and faster to do everything. I have no idea what to do with Python. If you want consistent Python (so that the libs don't fight) - put Anaconda and work on Spyder.
That's not what I mean. The trades are made on a very small end plot, and that plot, with a probability of about one, itself has nothing to do with the distribution and can behave as it pleases. The advantage on a large sample of such trades nobody cares or can care about. For a working TS a significant advantage is needed already on 3-4 trades.
I.e. it is fundamentally impossible to builda real TS on statistical regularities.
As many people, so many opinions. There are those who build a real TS only on statistical patterns. Not to be unfounded,Maxim Dmitrievsky recently gave a link to an article by Alexander Gorchakov. In his youtube he explains how he builds his real TS using theorists and matstat for twenty years.
There are as many people as there are opinions. There are also those who base real TC only on statistical patterns.Maxim Dmitrievsky recently gave a link to an article by Alexander Gorchakov, not to be unsubstantiated. In his youtube he explains how he builds his real TS using theorists and matstat for twenty years.
I went to his seminar about 5-6 years ago. He told me about his system and about long tails. He had nothing, and had never had anything. He is now the head of the investments department at Finam and is generally out of the game, like all the bosses). Now you can remember the system and the battles they were fighting.
I'm removing python and putting R again, just for the sake of statistics :D
There's SageMath, where you can combine the two. There's also something similar written in Python.
There is SageMath, where you can combine the two. There's also something similar written in Python.
Judging by the description, there is, and many things, and not only in Python.
It's not even a question of... if there's "something else like that...", but what exactly do you need? What is missing? One chooses from this, not from something exotic somewhere.