Adaptive digital filters - page 12
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
All the more so if the broker will get there. That's what I was writing that quotes are practically noise-free. Piligrimm a couple of pages ago correctly explained that brokerage companies add something that can be called "noise", but it is the spread that is incommensurably smaller than the amplitude of the price movement, so let's just ignore it. :-)
Does that mean that the DC input is the "true" price? Is that what it is? It's a nightmare on the input side.
From my point of view, it is very similar to the system of expert assessments, when you gather a bunch of people and ask them one particular question. Let's say "What is Putin's salary equal to?" and each expert, not knowing her "true" salary, gives his estimate (a number). The market arbitrates out the experts who are too stupid. And the DC in this case acts as one of the experts, who also does not know the "true" price, but only gives his estimate, rounded off to the 4th digit.
And how precise is the DC's estimation of the "true" price (the real exchange ratio)? What is the confidence interval of this estimate ?
And pipsing has nothing to do with it, IHMO.
Just think, I already gave a link to the figure. I will repeat it here. Suppose we need to predict the line y(x)=a*x+b. The worse is the measurement (estimation) of this curve in each analyzed point. The worse our prediction is, and the magnitude of the prediction error increases with time.
Well that's easy, take 50 true straight line points. And apply a noise with the variance of 2 pips to them and forecast the straight line by these data. And then take the variance not of 2 pips, but 200 and predict it too.
And then answer who will engage in scalping: the one who has a prediction of the rate for a day forward with an accuracy of +-20 points. Or the one who forecasts 15 minutes ahead has accuracy three paws to the right of the sun :-).
That's why I think, before making forecasts, one should get the most accurate estimation of that unknown price from all quotes available for analysis. And the accuracy should not be neglected.
The right-hand side of the charts is about the same time. Now tell me: what confidence intervals can we talk about with such a difference in quotes! What criterion are you going to use to select a "decent" brokerage company?
The only decent one for me is the one who will pay me as much money as I have. Who will pay me money no matter how much I earn. The one who fulfills his public offer.
And if the DC's estimate of that "true" price is worse + issued with a delay, then that's the DC's problem, not mine. Let him ask me for a job :-) And I will set filters for him :-)
Except that no one knows the real exchange rate, except maybe Bernanke (and he is unlikely).
Mathemat, radar also has no way of knowing the real distance to the target. So the situation is perfectly standard and is a subject of a science called matstatistics. Another issue is that this science is more fond of Gaussian distributions.
Except that no one knows the real exchange rate, except maybe Bernanke (and he is unlikely).
Mathemat, radar has no way of knowing the real distance to the target either. That is, the situation is perfectly standard and is the subject of a science called matstatistics. Another issue is that this science is more fond of Gaussian distributions.
Prival, you too consider the broker's offer not the true price, but his expert judgement. Well, dear friends, wait until the broker's price equals the
otherwise you will not be able to make a deal at the price calculated according to your forecast!
Well, dear ones, wait until the broker price equals the true price - otherwise you will not be able to make a deal at the price calculated by your prediction!
Well, dear ones, wait until the broker price equals the true price - otherwise you won't be able to make a trade at the price calculated by your prediction!
I have not been able to find any results of actually applying the Kalman filter to the analysis of quotes.
Prival, you also think the broker's offer is not the true price, but his expert judgement. Well, dear ones, wait until the broker's price equals the
otherwise you will not be able to make a deal at the price calculated according to your forecast!
Well Mathematician was scary :-)
I've got scarier pictures than that. The red dots are the radar input (measurement stream) Fig.1. But Fig 2 is the output of the Kalman filter (what he selected from that stream). One of its successful applications.
Fig.1
Fig.2
So the dog in filtering has eaten a bit.
Z.I. These are graphs from my articles, to be published this month in Fazotron (Hardware-software complex for determining the speed of small and hypersonic objects) and in Vestnik of Computer and Information Technologies. All open printing.