How can I tell the difference between a FOREX chart and a PRNG? - page 13
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
For all theorist and matstat, of course, I do not dare to answer, but in correlation and regression analysis with the problem of multicollinearity of factors are struggling and quite successfully. Why "danger"? Not danger, but checking and transforming.
Well, try it, and please share the results with us here. Others have tried, they haven't succeeded yet. They lack precision.
And then, as many statisticians there will be as many conclusions, of varying accuracy. And the accuracy of 0.1%.... 1.0% accuracy on a short period, as it is necessary for retail Forex, no one will give.
Professor Orlov explicitly warns on his site that he is not engaged in forecasting of price series time series. And he certainly knows where he can get results and where he cannot. And for sure he is regularly approached with monetary offers of such work.
E; I don't know if this is a topic or not, but since it's necessary to impress the science savvy people, it might be interesting, although I don't know).
The link to a post where UP on forexclub forum publishes his mathematical proof that profitable trading is possible on forex. And (!) not as a result of breaking the Markov process, but just based on the assumption that it is a perfectly random, i.e. Markov process.
The actual link is http://forum.fxclub.org/showthread.php?t=22097&page=3
Comrade, all this, of course, cool, but even a well-calculated martingale scheme assumes that you have an infinite amount of money initially. Then yes, you can earn by this method (but do you need it, with infinity in your pocket?).
And here I draw attention to the inconsistency of the post due to a logical fallacy in the calculations: considered the distribution of one-hour candles (and the probability is calculated on it), but the market offered to sit "until blue in the face", which with the stated stop-loss can last for years. So the "mathematician" gets a C minus for trying.
I sense a certain unfriendliness in your questions. I usually end the debate immediately. But for you I'll make an exception and answer:
1. The correlation between two bars of the M15 timeframe is an autocorrelation of the series, which is between fifteen bars of M1. The correlation of the bars of the larger timeframe is the autocorrelation of the bars of the smaller timeframe, its microstructure. Add here the fact that the quotes received by you are already filtered, i.e. they already have the Slutsky Effect. Maybe that's why Privalov wanted unfiltered tick quotes so vehemently, and got banned for that (I'm more relaxed about the tick problem).
2. I don't know what "non-marking" is. Tautologies of flawed flawed speculative scholastic mathematical theories have never interested me.
3. not enough. Something else is needed.
4. TA. I can repeat again (see above) what is written in almost any probabilistic inference, and why POSTLY there are no methods for handling highly correlated "random" series in theor-ver (it's just exactly a belief, like in a cult). Professor Orlov (a well-known practitioner of probability theory, author of many articles, journal editor, and author of books) writes about this too, clearly warning about the dangers of applying statistics to economics.
Correlation dependence is a type of statistical dependence and usually makes practical sense for stationary series. What in pricing allows you to talk about autocorrelation of increments? I.e. from where:
So to start with - you have to consider that correlation between supposedly random price quotes IS, and then proceed from that.
Why they are there - in the pricing threads.
Well, try it, and please share the results with us here. Others have tried, they haven't succeeded yet. They lack precision.
And then there are as many statisticians as there are conclusions, of varying accuracy. And the accuracy of 0.1%.... 1.0% accuracy on a short period, as it is necessary for retail forex, no one will give.
Professor Orlov explicitly warns on his website that he is not engaged in forecasting of price series time series. And he certainly knows where he can get results and where he cannot. And probably he is regularly approached with monetary offers of such work.
And why try - I use them.
Conclusions of varying accuracy - I don't know of such a thing. there is a regression model, for example. There is a coefficient of determination R2 - is that what you mean by accuracy?
About the professor - there is a difference between a theorist and a practitioner. About the application of people with degrees in technical sciences without knowledge of economics, Taleb wrote well in "Fooled by Randomness".
Demi:
On the application of people with degrees in technical sciences without knowledge of economics, Taleb wrote well in "Fooled by Randomness".
So every book he wrote was about how 95% of people are idiots. But we already know that, don't we?
Correlation dependence is a type of statistical relationship and usually makes practical sense for stationary series. What in pricing allows you to talk about autocorrelation of increments? I.e. from where:
About terms, sectarianism in mathematics etc. - it's not in the mathematics itself, but in its misapplication to specific subject areas. Not defending it or suggesting it should be applied to the trade - just for objectivity's sake.
I am laughing. Of course, I am not laughing at you, my friend, but at the typicality of the situation, where your, colleagues, discussion has reached.
You have just HAD to answer your own question. Your proposition number 2 answers the question in your proposition number 1. We're moving into the realm of linguistics here, but that's not my fault. Gödel and Church gave mathematicians a powerful weapon against entering tautological dead ends. (The way out of them is given by the Bible, but we will not apply it here yet.) Kolmogorov with his alleged "axiomatics" has prepared a huge hole near the path of the probabilists. You can not fall into it only by going back to the original way of solving the real problems of the real world.
And the solution is simple:
Correlation is NOT A CAUSATION.
So Correlation is not a causal relationship. It's just a MEASURE (be careful with that word), a computable measure of true causality between phenomena, i.e. correlation is a measure of LAW.
There is no "correlation dependence", there is JUST a CAUSATION between phenomena. And correlation is a number to measure that dependence. If I wrote "correlation" here, it only meant that I knew the NUMBER to measure that dependence. I'm sure you, my friend, knew it without me, but just succumbed to the bait of the general "stationarity" around here. And in statistics and theorists in general "people and horses are mixed up".
So what? And then the theorver begins a tautology: if we start parsing the notion of "stationarity", it will eventually come to itself (within the framework of Kolmogorov's axiomatics and the now accepted principles of theorver).
And after a thousand simple questions "why?" and "so what?" You will find that you are moving in a vicious circle - and therefore in volatile systems (like quotes) the theorist does not work and predicts nothing.
So he has every book about how 95% of people are idiots. But we already know that, don't we?
I am laughing. Of course, I'm not laughing at you, my friend, but at the typicality of the situation where your, colleagues, discussion has gone.
You have just answered your own question. Your proposition number 2 answers the question in your proposition number 1. We're moving into the realm of linguistics here, but that's not my fault. Gödel and Church gave mathematicians a powerful weapon against entering tautological dead ends. (The way out of them is given by the Bible, but we will not apply it here yet.) Kolmogorov with his alleged "axiomatics" has prepared a huge hole near the path of the probabilists. You can not fall into it only by going back to the original way of solving the real problems of the real world.
And the solution is simple:
Correlation is NOT A CAUSATION.
That is, correlation is not causation. It is merely a MEASURE (careful with that word), a computable measure of a real causal relationship between phenomena, i.e. correlation is a measure of LAW.
There is no "correlation dependence", there is JUST a CAUSATION between phenomena. And correlation is a number to measure that dependence. If I wrote "correlation" here, it only meant that I knew the NUMBER to measure that dependence. I'm sure you, my friend, knew it without me, but just succumbed to the bait of the general "stationarity" around here. And in statistics and theorists in general "people and horses are mixed up".
So what? And then the theorver begins a tautology: if we start parsing the notion of "stationarity", it will eventually come to itself (within the framework of Kolmogorov's axiomatics and the now accepted principles of theorver).
And after a thousand simple questions like "why?" and "so what?" You will find that you are moving in a vicious circle - and that is why in variable systems (like quotations) the theoretician does not work and does not predict anything. Let's not elaborate as this is an offtopic.
So by correlation you mean any dependencies at all and different ways of evaluating them? Usually correlation is quite specific types of dependencies, while the presence of any dependencies between members of a series is called non-markness. You don't like the term, so what the hell with it, although there is no sectarianism there))
About the theorver - didn't suggest using it. The pricing model is primary, the methods of using it are secondary. If the model is real, as a rule, high mathematics is not necessary to use it, nor are its practical applications in other areas.
Let me guess - crowd effect (positive feedback). Everyone buys -> the price goes up -> everyone buys. Naturally, locally and short-term, until the "fuel" for the process runs out.
Here much depends on the specific market. On its type and its microstructure. That is, the rules of trading and how participants make (try to make) a profit. Who trades and how, to put it simply.