Machine learning in trading: theory, models, practice and algo-trading - page 842
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
Then it is easy to reject the whole study. The results on different sources of tick data will be different.
Moreover, there is a clear misunderstanding of what a tick is. On such a foundation it is nothing to talk about returns.
Knowing the basics of pricing, you can create any number of ticks.
I've already mentioned that, and the data can be absolutely different. So, it's possible to get two radically different grails, that will work by the principle of a coin flip, and the ticks will be counted only for self-reassurance.
hello!
these inferences do not predict beyond the variance...
What is the graality of the distribution shown? Are you saying that if one piles up any imaginary tick story with such a distribution, there is a TS (which one?) that shows the graality of that story?
This statement fits well with current geopolitical realities, but not with the scientific approach.
I'll try to cut in, I believe this is the attempt to restore the original distorted tick stream. I support Alexander's method.
I will try to cut in, I believe that this is an attempt to restore the original distorted tick flow. I support Alexander's method.
So, it won't work for stock quotes, right?
It is necessary to check, never say no. This is an attempt to bring to stationarity from the origin, the desire for a Gaussian distribution in incremental returns is already a consequence.
I will try to cut in, I believe that this is an attempt to restore the original distorted tick flow. I support Alexander's method.
I wrote to your coryphaeus, but he did not answer.
The tick flow, which you supposedly restore, is always different: you cut, for example, took ticks 1,2,4,7..... And then the window moves, there will be a new tick with number 1, with number 2 (in my numbering) will coincide with the tick that had number 1, and then tick 4 will be taken, which previously had number 3? And so on, i.e. every time the window moves, you will have a different sample (a different set of ticks) for your statistics.
There is no talk about restoring some "real" set of ticks. Moreover, it suggests to trade on the variable set of ticks. And where's the reasoning that it's very graalistic?
I wrote to your coryphaeus, but he did not answer.
tick flow, which you supposedly restore, all the time is different: thinned, took for example ticks 1,2,4,7..... And then the window moves, there will be a new tick with number 1, with number 2 (in my numbering) will coincide with the tick that had number 1, and then tick 4 will be taken, which previously had number 3? And so on, i.e. every time the window moves, you will have a different sample (a different set of ticks) for your statistics.
There is no talk about restoring some "real" set of ticks. Moreover, it is proposed to trade on a variable set of ticks.
The reading is done by this algorithm: https://www.mql5.com/ru/forum/221552/page143#comment_6371064
The reading is done by this algorithm: https://www.mql5.com/ru/forum/221552/page143#comment_6371064
I'm not discussing the algorithm in detail, what matters to me is that the scale is non-uniform, which means that the history for the most recent tick changes as the window moves and with an exponent most likely never matches.
I will try to cut in, I believe that this is an attempt to restore the original distorted tick flow. I support Alexander's method.
And who proved that the flow is distorted and on what grounds?
I would listen to arguments such as
And who proved that the flow is distorted and on what basis?
I would listen to the arguments, for example
Get out of here.