Optimal strategy under statistical uncertainty - unsteady markets - page 4
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
don't sweat it, Ezh... the man just has to discover cluster analysis...
HideYourRichess, don't overestimate, there are challenges of their own...
I can make a correction by informing you that there are also sideways trends, which will render your p. 2 will make it practically useless. You didn't take this into account and therefore formulated a strictly trend following strategy, which in no way can be fully implemented.
You could agree, but no. If you don't limit yourself to one timeframe, there is always something where there is a trend. And we should not forget about multicurrency. It's very rare when the market is standing still. Another thing is that the profitability of the system is low.
HideYourRichess, don't overestimate, there are difficulties of their own...
Explain.
On page two of this thread I gave you an example, which you ignored.
Here's another example for you:
OROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROROR
The total number of outcomes is 20, heads - 10, tails - 10.
Here we have: p=0.5 and q=0.5.
What zero expectation of winning by your proposed system can we talk about?
The system is not mine, and its author, as already found out, is (c) Claude Shannon.
If you want to give special cases, I can also give a counter-example of one of special cases of the sequence:
PPPPPPPPPPOOOOOOOOOOOOOOOO
>> Explain.
>> oh... Mtatemat can explain it better... but the main difficulty is just finding the wrong coin...
Oh... Mtatemat can explain it better... but the main difficulty is just finding the wrong coin...
That wasn't what it was about. It was about general principles. At least for me. The general principles are like this. And the practice of applying them may differ.
Oh... Mtatemat can explain it better... but the main difficulty is just finding the wrong coin...
Well, theoretically this coin can be searched directly with this strategy :) . So the difficulty is about the same as finding a profitable strategy in general.
Yes, cluster analysis is too broad, what exactly did you mean?
The system is not mine, and its author, as we have already found out, is (c) Claude Shannon.
If you feel like citing special cases, I can also cite one of the special cases of the sequence as a counter-example:
PPPPPPPPPPPPOOOOOOOOOOOOOOOO
Yes, that's also an example with a non-zero expectation of winning. So I'm asking, where does the zero-maturity expectation assumption come from?
what do you mean exactly?
I must admit that I'm only familiar with it from Mathemat's (and Rosh's) articles... I haven't really studied this topic yet... but I'm planning to (no time at all at the moment)...
HideYourRichess, well, try it, study with Bernoulli... I won't scare you too much... maybe it will work out...
PS. if Mathemat hasn't become a millionaire yet, then it's not all that easy there...
Yes, that too is an example of a non-zero expectation of winning. So I'm asking, where does the assumption of zero expectation come from?
Well, it's obvious. You yourself got 50% successful guessing in the extremum, i.e. in essence the game turns into a regular random.