a trading strategy based on Elliott Wave Theory - page 208
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
Sergey, thanks for the clarification, I didn't know that the price series is already integrated first order. This is news to me in a way. Is there any justification for this statement?
We only analyse stationary time series. Price series are not stationary - they do not have a constant expected payoff. However, it is reduced to the stationary series of residues X[i] by a single differentiation:
X[i]=Open[i]-Open[i+1].
This is usually an exponentially distributed random variable with zero expectation and a sign-variable correlogram. The original series can be recovered from the residue series by simply integrating them:
Open[i]=Open[i+1]+X[i]
This is the reason why the price series can be called an integrated time series of the first order.
I disagree with the statement that it all comes down to predicting only one direction of price movement. Having guessed/predicted/calculated (as you wish) the direction one needs to figure out how long to hold a position, or even a correct prediction may not help. The second point is especially important, especially as I figured you are saying, that it is impossible to make a forecast for a long term (by the way, if you could define the quantitative expressions, maybe I missed it somewhere).
For a particular TS we can determine the average time of holding T open positions. Then we can convert the original time series (for example, minutiae) to TF=T, thus obtaining a scheme where we open (if necessary) at the opening of the next candle and close at its closing. All we need to know is the sign or colour of the expected candle, as we can statistically estimate its size from the standard deviation:
The probability of the price jump being less than one standard deviation for this TF is about 68%.
The probability that the price jump is less than half of the standard deviation is 38%.
The probability of the price jump being less than a quarter of the standard deviation is 20%.
You can see that the prediction problem in this formulation is reduced to predicting ONLY the expected direction of the price movement after the position opening or the sign of the price jump or, similarly, the colour of the next candle.
.
I guess it will eventually come down to "trend" and "noise", that would be the model. So maybe it's time to move on to criteria or do you have a better idea? :o)
It won't exactly come down to a trend, since there isn't one... But there are better ideas.
...Don't mean to pry, explain to me where you get the sliding window in the autocorrelation calculation and what's the point and use of it. Or it is some kind of modification for some task?
At one time I wrote an indicator based on FAC, that's what I needed a sampling window for. It could be a sliding window, it could be a stepping window... as you like, or you can do nothing at all :-)
Alex Niroba 08.01.07 21:36
Forex is first of all people, or MTCs, which are also developed by people :)))
Do you really think that most traders do
this nonsense!!! :)))))))))))))))))))))))))))))))))))
Neutron , my dear friend, don't consider it rude !!! :)))))))))))))))))))
Alex, without proof, but it can be considered a credible fact that most private investors in the forex market are losing their deposits. Why do you think so? Maybe because this majority do not do this very "bullshit"? That's a paradox, dear fellow. Especially when you consider that the majority, it's about 99%.
In my opinion this is only possible in one way. In the same way as the transition from the microscopic description of dynamic systems in Newton's theory to their macroscopic description in thermodynamics. But to do this, we must see the market as a holistic system, one of the intrinsic properties of which is the price. And instead of trying to tie the price to individual events that take place on the market (the news release, for example), we must try to find other, also macroscopic, means of describing this system.
The role of experts in the field of mathematical statistics is probably the most important one. After all, the development of thermodynamics (statistical physics) and mathematical statistics were things interrelated and interdependent.
Beautifully put!
If in physics the laws determining mechanisms of interaction of bodies play the main and only role in construction of the complete theory, and the laws of thermodynamics became the limit transition, then in the market this role, it seems to me, should be taken by the laws determining character of interaction (connection) of direction of the expected jump of price from the previous...
Can you share your thoughts? :о)
I can't agree with you that trends don't exist for forex. That they are hard to find (or rather convincingly prove) I agree, but I see no reason why a trend cannot exist. The above arguments, for me (I emphasize that for me) do not prove the absence of trends as such, but only convince of the limited knowledge of Nature. (a bit philosophical :o)
Any modification of autocorrelation estimates only a conditional relationship between samples, and this figure by itself, of course, does not yet indicate the presence or absence of a trend.
Посмотрите на их календарь точек разворота и на дневной график 2006.
Даже в январе-феврале (а прогноз сделан в декабре 2005) они ошибаются.
...
the authors claim that almost all of their predictions for this year have come true. i have not verified them myself. here is a quote:
"...And so. The result, which gave the most banal methodology exceeded my wildest expectations.
For now, 24 out of 30 predicted points have worked "correctly". Some simple mathematical operations showed that it was 80% of coincidence. Moreover, there are only 3 forecast points left until the end of the year, i.e. in the worst case scenario the accuracy of the calendar reading will be approximately 73% ...".
http://forum.viac.ru/viewtopic.php?p=81395#81395
North Wind are you really that naive and believe that someone will leak a profitable system to the internet :)))
If the system gave 80% matches these two guys with a bunch of girls would be resting on their own island somewhere in the Pacific Ocean, drinking pumpkin and smoking cigars :))))
Not too lazy to look again substantively. Pictures are attached.
If you count the match with an accuracy of (+/-)1 bar, you get 11 hits out of 33. That's 33% - generally speaking a very good result, but it's not the claimed 73%. The problem, however, is that you have to count to actual pivot points, I believe. And they haven't defined what they consider a trend change.
It's me who has set the zigzag parameters where these pivot points are of the same order of magnitude as they are. So it is impossible to objectively assess these results at all.
Northwind are you really so naive and believe that someone will leak the profitable system to the Internet :)))
If the system gave 80% matches, these two guys with a bunch of girls would already be relaxing on their own island somewhere in the Pacific Ocean, drinking pumpkin and smoking cigars :))))
1. it seems that you tend to draw far-reaching conclusions from completely insignificant assumptions, and that's wrong.
2. whether the system is profitable or not - personally I don't know, but the description shows that the authors, based on published methods, have made an attempt to predict any characteristics of price movements. and according to their data, the success of predicting these characteristics was 73-80%. that's all that the article talks about and more. it's not about any profit systems or anything else.
3. all methods used are elementary and described. recall that here, just above the subject, the issue "for non-househusbands" was raised - a demonstration of this approach. and by people who, to put it mildly, understand something about the mathematical methods they use.
4. I hope I have made my position clear enough.
Neutron can't judge others.
Why are the deposits being drained?! Good question.
If you don't have a clear system, by which you trade, you will anyway sell :))),
no matter how much you earn, the amount doesn't matter
10 thousand or 600 million - it's all the same...
If you increased your deposit from 5 koz to 95 koz this month,
it's not certain that you won't blow it one week later,
somewhere you'll forget to put a stop loss or overload a position
and you'll end up losing everything. It's like a casino.
It's all down to greed. :))))))))
It's easy to make money. The main thing is NOT to lose it !
That's why you need to develop a clear strategy with stop-losses :)
That's what I'm working on now...
Северный Ветер неужели вы так наивны и полагаете, что кто-то сольёт в Инет профитную систему :)))
Если бы система давала 80% совпадений эти бы два парня с кучей гёрлз уже бы отдыхали на собственном островке, где нибудь в Тихом океяне, попивая тыкулу и покуривая сигары :))))
1. it seems that you tend to draw far-reaching conclusions from completely insignificant assumptions, and this is wrong.
2. whether the system is profitable or not - I personally do not know, but the description shows that the authors, based on published methods, have made an attempt to predict any characteristics of price movements. according to their data, the success of predicting these characteristics was 73-80%. this is all that is discussed in the article and below. it is not about any profitable systems or anything else.
3. all methods used are elementary and described. recall that here, just above the subject, the issue "for non-househusbands" was raised - a demonstration of this approach. and by people who, to put it mildly, understand something about the mathematical methods they use.
4. I hope I have made my position clear enough.
North Wind yes, your position is stated quite clearly. :)
But you yourself said earlier that you didn't check their predictions, then why rub us the wrong way!? :)
One thing I can say is that it is one thing to give out forecasts and quite another to trade according to those forecasts!!!
Just like there are theorists and there are practitioners :)))
Well said!
If in physics the main and only role in construction of the complete theory is played by laws determining mechanisms of interaction of bodies, and which limiting transition became laws of thermodynamics, in the market this role, it seems to me, should be taken by laws determining character of interaction (connection) of directions of expected jump of the price from the previous...
I couldn't agree more. It's still a microscopic approach. Even if you integrate the whole process inside a candlestick, forming candlesticks according to the average holding time of a position or whatever, by doing so you are simply moving to another fractal level. From my point of view, this approach is good for model evaluations but not for dynamic market analysis. I see two disadvantages in it.
1. The process stochastics are hidden inside the candle and therefore can't be a source of information. Whereas actual measurements of those macro variables that can describe market conditions should dynamically rely on that stochasticity.
2. By shaping the candlesticks in this way you are imposing a certain period on the market. But you stated yourself that the spectrum has no stationary components. So such candlesticks will not light up anything and the market will not like it. :-))
Not too lazy to look again at the subject. Pictures are attached.
If you count the match to the accuracy of (+/-)1 bar, you get 11 hits out of 33. That's 33% - generally speaking a very good result, but it's not the claimed 73%. The problem, however, is that you have to count to actual pivot points, I believe. And they haven't defined what they count as a trend reversal.
...
Interesting pictures, but unfortunately, personally, I still don't understand what was predicted. They report a "possible change in dynamics", what is underneath it - I can't judge. It would be a good idea to ask the authors. There is Fig.5 in the article, so it does not coincide with the zigzag.
But, I gave references not for this purpose. Personally, I am much more interested in what techniques and why, the authors used.
Zy: if the pictures were a little smaller in size, it would be perfect.
By the way, the accuracy of +/- 1 bar is about 1\250, i.e. 0.4%.
Interesting pictures, but unfortunately I still don't understand what was predicted. They report a "possible change in momentum", what's underneath that - I can't judge. It would be a good idea to ask the authors. But that's not why I gave the links. Personally, I'm much more interested in what techniques and why the authors used.
Note: if the pictures were a little smaller in size, it would be great.
[/quote]
North Wind If you yourself don't understand or don't understand it to the end, why defend this method? :)))
Z.U. Smaller pictures, bigger font!
Wings, legs! The main thing - the tail!!! :)))