Distribution of price increments - page 17
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
Is that what you mean?
And was it worth transferring the paper? ...
for one row Bid, no row Ask. Where did the idea of a spread come from?
I meant "nonparametric skew"
for one Bid row, no Ask row. Where did the idea of a spread come from?
Dear traders!
I consider the topic closed. I have solved the problem set by my daughter and with your help (at least for me).
Until the New Year I will be programming in intensive mode and will appear on the forum very rarely.
Special thanks:
Vladimir
Yuriy Asaulenko
Aleksey Vyazmikin
Thank you!
P.S. For those traders who are interested in this topic, and in general by nature curious and persistent - once again carefully reread all the threads in the discussion of which I participated, as well as the themes of those traders who have also participated in these unforgettable scientific debates.
Thanks again!
Regards,
Alexander_K
Dear traders!
I consider the topic closed. I have solved the problem set by my daughter and with your help (at least for me).
Until the New Year I will be programming in intensive mode and will appear on the forum very rarely.
Special thanks:
Vladimir
Yuriy Asaulenko
Aleksey Vyazmikin
Thank you!
P.S. For those traders who are interested in this topic, and in general by nature curious and persistent - once again carefully reread all the threads in the discussion of which I participated, as well as the themes of those traders who have also participated in these unforgettable scientific debates.
Thanks again!
Regards,
Alexander_K
I would not be surprised if after the New Year a paid product will appear in the Market
Dear traders!
I consider the topic closed. I have solved the problem set by my daughter and with your help (at least for me).
Until the New Year I will program in intensive mode and will appear on the forum very rarely.
Special thanks:
Vladimir
Yuriy Asaulenko
Aleksey Vyazmikin
Thank you!
P.S. For those traders who are interested in this topic, and in general by nature curious and persistent - once again carefully reread all the threads in the discussion of which I participated, as well as the themes of those traders who have also participated in these unforgettable scientific debates.
Thanks again!
Regards,
Alexander_K
You're not even talking about the solution of the problem, because you have made a typical mistake: "solving a wrong problem with the right methods".
On what basis have you decided that there are regularities in financial markets in general and Forex in particular? You have to prove it, and you have taken it as an axiom.
But if we assume the contrary: there are no regularities on financial markets then all your ideas go down the drain.
And the thought about absence of regularities on financial markets is today a basic one for using statistics on financial markets and it is called in a simple way: non-stationary processes.
If you pay attention to the results available on financial markets, in particular if you use GARCH models, you'll be surprised to see that the parameters you're trying to find are random variables and these parameters exist only if their error is distributed normally, which is not always the case! That is, you calculate the parameters of the Student's distribution you mentioned, and these same parameters either exist or do not exist. There are special tests on stability of parameters of these very parametric models, i.e. not of types of distributions, but of parameters of these distributions, in order to find out this problem.
And these are not all gifts.
Changes in model parameters come in waves, and the period of this wave is also random.
You are not even talking about solving the problem, because you have made a typical mistake: "solving the wrong problem with the right methods".
On what basis have you decided that there are regularities in financial markets in general and forex in particular? You have to prove it, and you have taken it as an axiom.
But if we assume the contrary: there are no regularities on financial markets then all your ideas go down the drain.
And the thought about absence of regularities on financial markets is today a basic one for using statistics on financial markets and it is called in a simple way: non-stationary processes.
If you pay attention to the results available on financial markets, in particular if you use GARCH models, you'll be surprised to see that the parameters you're trying to find are random variables and these parameters exist only if their error is distributed normally, which is not always the case! That is, you calculate the parameters of the Student's distribution you mentioned, and these same parameters either exist or do not exist. There are special tests on stability of parameters of these very parametric models, i.e. not of types of distributions, but of parameters of these distributions, in order to find out this problem.
And these are not all gifts.
Changes in model parameters come in waves, and the period of this wave is also random.
You are not even talking about solving the problem, because you have made a typical mistake: "solving the wrong problem with the right methods".
On what basis have you decided that there are regularities in financial markets in general and forex in particular? You have to prove it, and you have taken it as an axiom.
But if we assume the contrary: there are no regularities on financial markets then all your ideas go down the drain.
And the thought about absence of regularities on financial markets is today a basic one for using statistics on financial markets and it is called in a simple way: non-stationary processes.
If you pay attention to the results available on financial markets, in particular if you use GARCH models, you'll be surprised to see that the parameters you're trying to find are random variables and these parameters exist only if their error is distributed normally, which is not always the case! That is, you calculate the parameters of the Student's distribution you mentioned, and these same parameters either exist or do not exist. There are special tests on stability of parameters of these very parametric models, i.e. not of types of distributions, but of parameters of these distributions, in order to find out this problem.
And these are not all gifts.
Changes in model parameters come in waves, and the period of this wave is also random.
Indeed, what is there to theorize about! We trade on one wave and that's it!
What's there to theorise about! We trade on the same machine and that's it!
I'm just kidding around, but when you think about it there's nothing funny ))))
Of course, there is nothing funny.
Today we can distinguish two qualitatively different directions for building decision-making blocks in TS: trading by patterns (TA and machine learning), taking into account statistical characteristics of quotes - the most developed one is GARCH, which is several tens of years old.
Instead of taking one more step from what has been achieved, there are always some theoretical constructions performed by competent people from other fields of knowledge. At the same time these people do not think about the reasons of existence of all these GARCH, when there are ordinary statistics and Fourier.
That's why we get such branches with an alchemical smell.
The task was certainly not an easy one. I should say that this distribution is not one of the widely discussed ones - neither normal, nor logistic, nor Laplace, nor Cauchy, etc., etc.
But probably the closest to Laplace, if about returns, besides there is a simple theoretical justification, return is in fact an expression of opinion by a deal, and the size of the deal depends on the wealth, which on average is exponentially distributed and if all investors from small to large start hitting the market, you get pure Laplace.