From theory to practice - page 339
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
It is possible to predict the next value if it depends on something, such as time, or previous values (which is what Kolmogorov says), or another value. The RNG does not have such a dependence, the market sometimes does. For RNG (a stationary value), you can predict the mean and variance, for which distributions are studied. For the market it is necessary to study the dependencies. A_K2 may realize it, but it always expresses itself as if it is working with the price as with RNG.
But if for example, hypothetically, using some kind of non-linear transformation our trousers turn into elegant shorts))) Ah, my point))) Yes, BP is transformed by some kind of transformation into GSR, and then what? Your answer))) That's basically what Alexander is trying to get at. If such a way of transformation could be found, the ability to predict would not be long in coming).
turns into BP by some kind of conversion to HCP, and then what?
Turning BP into HCPs would make it impossible for you to earn anything at all, in principle)
Faced with outright downanism, in the form of the claim that you cannot predict random number series with an Erlang distribution, I am forced to leave the forum for good. If you want it, you'll find my wife's personal account, I'll be in touch there from time to time.
Thanks to: Warlock, Doc, Nova and people like you who supported me during my 6 months on the forum. If it gets tough, the wooden Grail is at your service. Will there be a golden Grail? There will be. I, with Schrodinger's cat, am going to follow it on a long journey.
Sincerely,
Alexander_K.
Faced with outright downanism, in the form of the claim that you cannot predict random number series with an Erlang distribution, I am forced to leave the forum for good. If you want it, you'll find my wife's personal account, I'll be in touch there from time to time.
Thanks to: Warlock, Doc, Nova and people like you who supported me during my 6 months on the forum. If it gets tough, the wooden Grail is at your service. Will there be a golden Grail? There will be. I, with Schrodinger's cat, am going on a long journey to get it.
Sincerely,
Alexander_K.
You can get out of forex in two cases:
1. Go out defeated. This is at any time.
2. Exit victorious and walk away at the end of your life.
in the form of a statement that you cannot predict a series of random numbers with an Erlang distribution
If you really want to, you can. )))
Then all that was needed was a simple example of such prediction - a random Erlang flow is generated and then the subsequent values are predicted, without too much chatter.
or, in other words, how to predict the average value? will the prediction not coincide with the average?
The author claims, backed up by a degree in physics, that he can accurately predict the continuation of BP, i.e. calculate all subsequent BP values in the future.
Obviously, the average does not need to be predicted, it is already known.
how do you predict a stationary process with a fixed variance?
or, in other words, how do you predict the mean? won't the prediction coincide with the mean?
@Dr. Trader has the answer here.
https://www.mql5.com/ru/forum/221552/page338#comment_7241479
I haven't seen that statement anywhere
https://www.mql5.com/ru/forum/221552/page338#comment_7236473
If there's only one noise left, no. But it is unlikely that there will be one noise left.
Who said that? Bullshit.
https://ru.wikipedia.org/wiki/%D0%93%D0%BE%D0%BC%D0%BE%D1%81%D0%BA%D0%B5%D0%B4%D0%B0%D1%81%D1%82%D0%B8%D1%87%D0%BD%D0%BE%D1%81%D1%82%D1%8C
even if the series is heteroscedastic, it is quite predictable
It is possible if there is a signal-curve with a constant distribution and the goal is to isolate the signal and remove the noise.
In this case, the goal is the opposite, to pick out the noise for prediction by removing the interfering signal that disturbs the noise distribution.
even if the series is heteroscedastic, it's quite predictable
that's nonsense... it is always the average that is predicted, not the BP values...