Statistics as a way of looking into the future! - 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
Well, firstly, the approximation is not a curve, but a hypersurface. Secondly, what do you offer us, my dear? You can see that our methods will lead us to starvation. Waiting for your salvation :)
I.e. if we can't get around on a crooked mare, let's try on a hyper-skewed mare...
Sarcasm aside, the question remains the same - why the hypersurface all of a sudden? What indicates that hypersurface saves the day?
Let's say we don't know the factors influencing the market, then what?
Time - why use it? For example, does the polynomial "know" the holidays in the countries of the traded instruments? Easter, second day, all Europe is asleep, volatility is close to minimum, i.e. there is no wind the whole day, so our polynom must take it into account (lunar calendar).
You have listed factors, not time, time should be used, but when the polynomial consists only of time t, it is no good
What indicates that the hypersurface is saving?
Dynamical Systems Theory.
You have listed factors, not time, time should be used, but when the polynomial consists only of time t, it is no good
Exactly, apart from the time series of prices we have nothing, we don't know the factors. I argue that time need not be used - it is superfluous, at least to a large extent. What do you think other than prices can be used as factors?
Exactly, apart from the time series of prices we have nothing, the factors we don't know. I argue that time should not be used - it is superfluous, at least to a large extent. What do you think other than prices can be used as factors?
One of the factors affecting gold is the dollar. The dollar is influenced by the Dow Jones index. Bond is influenced by gold. But I am not so sure about that, you have to ask experts.
Theory of dynamic systems.
For a start, do we need determinism in this?
And in general, personally for me, the theory of dynamic systems has the same relevance to the market as Mendel's laws. No more than that.
Don't misunderstand me, I'm not asking about the name of the "curve mare" (the Theory of Dynamic Systems) that you are going to ride on the market, but about why exactly did you decide that the Theory of Dynamic Systems is saving? If the Dynamic Systems Theory is something familiar to you, then you can easily explain on your fingers the philosophy and the essence of how the Dynamic Systems Theory uncovers the market and predicts the future. For me personally, the mechanistic transfer of Dynamic Systems Theory to the market is unacceptable just because the theory contains the words "predict the future behaviour of the system". What makes you think that the market will fall under Dynamic Systems Theory?
Exactly, apart from the time series of prices we have nothing, the factors we don't know. I argue that time should not be used - it is superfluous, at least to a large extent. What do you think other than prices can be used as factors?
О! Colleague, I completely agree with you here - NOTHING. I think we do not need anything except price to analyse it. Time is a superfluous parameter that only complicates this already complicated task, giving nothing in return, or almost nothing. In a word, the desire to use time in our model must be justified.
As for hyperhorses and other evil things, their existence and expediency of their exploitation seems not so difficult to understand. Let us proceed from the fact that it is impossible in principle to make money on a random process (theorem). We believe (without proof) that there are regularities in the market which are hidden in the price and the exploitation of which will allow us to earn. It only remains to formalize the concept of regularities. For us traders, only one quantity that characterizes the price series is significant - predictability of future movement, it does not matter over what time interval, it is important where and by how much (in general, it does not even matter how much, only where)! Since we don't have, by convention, anything in our hands, except the price series, we will analyze it alone, without involving news and economic factors. Thus, we input one or several parameters (indicator readings) and the symbol price reaction to these readings. If there is only one parameter, we have a functional parameter-price relationship. This dependence IS a priori, since we are here only for it! And our task is to establish it. If there is more than one parameter, the function becomes multidimensional and the surface it describes becomes hypersurface. There are known methods of hypersurface reconstruction, e.g. approximation.
We are solving exactly this problem of hypersurface reconstruction. What are you doing here if not the same thing?
One of the factors affecting gold is the dollar. The dollar is influenced by the Dow Jones index. The bond is influenced by gold. But I am not so sure, I have to ask experts.
Please explain the meaning of "one of the factors influencing gold is the dollar". The price of gold is usually taken in relation to the dollar, i.e. here all the gold-dollar influencing factors are already taken into account. Or should we use a dollar index that excludes any correlation to gold?
О! Colleague, I totally agree with you here - NOTHING. I believe that we do not need anything other than the price itself to analyse it. Time is a superfluous parameter that only complicates the already complicated task, giving nothing in return, or almost nothing. In a word, the desire to use time in our model must be justified.
As for hyperhorses and other evil things, their existence and expediency of their exploitation seems not so difficult to understand. Let us proceed from the fact that it is impossible in principle to make money on a random process (theorem). We believe (without proof) that there are regularities in the market which are hidden in the price and the exploitation of which will allow us to earn. It only remains to formalize the concept of regularities. For us traders, only one quantity that characterizes the price series is significant - predictability of future movement, it does not matter over what time interval, it is important where and by how much (in general, it does not even matter how much, only where)! Since we don't have, by convention, anything in our hands, except the price series, we will analyze it alone, without involving news and economic factors. Thus, we input one or several parameters (indicator readings) and the symbol price reaction to these readings. If there is only one parameter, we have a functional parameter-price relationship. This dependence IS a priori, since we are here only for it! And our task is to establish it. If there is more than one parameter, the function becomes multidimensional and the surface it describes becomes hypersurface. There are known methods of hypersurface reconstruction, e.g. approximation.
We are solving exactly this problem of hypersurface reconstruction. What are you doing here if not the same?
Quite right, we assume there is a pattern. I wonder if the methods proposed here assume anything else. Sort of by default, implicitly. For example, that we can calculate some distribution parameters and reconstruct the hypersurface based on them?