Why is the normal distribution not normal? - page 7
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
You think it's time to move from complete randomness to interdependencies,
They certainly exist, but how do they manifest themselves? I don't think the elementary model is very complicated.
you are such a challenge :o)
:)
Well, let's start by saying at least that I lied a little bit:
And the feedbacks are negative and multiplicative.
It's actually alternating. Let me explain.
Let us assume that we consider forex arbitrage. For EURUSD, for example, arbitrage loops of the "first generation" = EURGBP*GBPUSD, EURJPY*JPYUSD, EURCHF*CHFUSD, etc. form really negative feedback chains. The second generation for EURUSD, it is EURGBP*GBPJPY*JPYUSD, EURJPY*JPYCHF*CHFUSD, EURAUD*AUDGBP*GBPUSD etc. They form chains of positive feedback.
The number of chains in this case increases from generation to generation. For a limited currency basket it is not difficult to calculate their number and take them as coefficients,
But in practice the basket is unlimited, though obviously not infinite, i.e. the coefficients will have to be somehow shamanized (which is not bad, let good shamans prosper). :)
Next... you have to keep thinking genially and experiment a bit.... :))
zy. I'm sure the same principle remains valid for funds, despite the lack of such explicit arbitrage interdependencies in it.
>> zzy. I modelled a similar scheme for just three generations and got rows of "quotes" which clearly show Elliott waves. Which is an indication of the presence of dough in the model. ;)
Why do people take so much trouble with "forex distribution" :) In my memory so much bewilderment about its abnormality....
Because people all too often apply concepts that only apply to normal distributions to anything, without trying to think about whether they can. Bollinger bands and envelopes are from the same series. This is despite the fact that even in the best case price is a Wiener process, and not at all quasi-normal (with floating m.o. and constant s.c.o.). But price isn't even a Wiener process, and yet it's still there.
This is a kindergarten, for God's sake. Cubes, bricks, balls and other geometric figures are randomly put together in the hope that the resulting structure will be stable.
I have the impression lately that all classic indicators without any context of their use are the purposeful propaganda and propaganda of suckers. The less suckers think, the more money they can get. And then new ones will come. The cycle of suckers in nature...
:)
Let's start with the fact that I lied a little bit:
The link is actually alternating. Let me explain.
Let us assume that we consider forex arbitrage. For EURUSD, for example, arbitrage loops of the "first generation" = EURGBP*GBPUSD, EURJPY*JPYUSD, EURCHF*CHFUSD, etc. form really negative feedback chains. The second generation for EURUSD, it is EURGBP*GBPJPY*JPYUSD, EURJPY*JPYCHF*CHFUSD, EURAUD*AUDGBP*GBPUSD etc. They form chains of positive feedback.
The number of chains in this case increases from generation to generation. For a limited currency basket it is not difficult to calculate their number and take them as coefficients,
But in practice the basket is non-finite, though obviously not infinite, i.e. the coefficients will have to be somehow shamanized (which is not bad, let good shamans prosper). :)
Next... you have to keep thinking geniously and experiment a bit.... :))
I personally see it all in the form of a football,
And with the Euro 2012 qualification, of course (the last one is a joke) but you need to stop and think or we'll make a mess here.
No, I myself have a growing impression lately that all these classic indulators without the context of their use are purposeful propaganda and promotion of suckers. The less suckers think, the more money they can get. And then new ones will come. Circle of suckers in nature.
100%
I am getting quite profitable indicators by simple (well I lie, not quite simple:) contextualization of signals. Profitability is small but stable. It is quite possible to sum up packs of such signals and according to pseudo-science statistics to increase profitability. And without contextualization it is eta.... into profits of DC.
So...
The same as between a derivative and its function .
Thank you.
You know the velocity distribution. What's next? How does it relate to the price distribution?
I think that everyone can see that it is not normal and everyone understands it, but no one can understand what it means, for example, to create such a distribution.
Yes it seems to me to recreate it not so difficult. Only this task does not stimulate me, I do not see any money in it.
Well, I understand the nature of the process, and thank goodness. And why do I need an "average hospital temperature"? It is another diagnosis to make an individual diagnosis ... :))
Therefore I pass by the topic and go straight to filtering (i.e. contextualization) of signals.
Why people bothered so much with "forex distributions" :) In my memory so much bewilderment about its non-normality....
There is practically no mathematical apparatus for interpreting non-stationary processes.
All these regressions, MLE and other estimators - they are all calculated from some particular cases of stationary processes distributions
Well, that's understandable.
There is practically no mathematical apparatus for interpreting non-stationary processes.
All these regressions, MLEs and other estimators - they are all calculated from some particular cases of stationary process distributions
I don't think there's one that's freely available. :)) And in the proprietary - there are a lot of developments. Only... Where would I go with such a tool if I had one (let's suppose that I don't have it now:) ?
Right, forex. Well, is it really for the paltry Nobel Prize?
// (looking modestly at the floor, scratching the machine with my right hand and drawing circles with the toe of my left foot...) :
- That's why I'm here........
:))
Because people all too often apply concepts that only apply to normal distributions to anything, without trying to think about whether they can. Bollinger bands and envelopes are from the same series. This is despite the fact that even in the best case the price is a Wiener process, and not at all quasi-normal (with floating m.o. and constant s.c.o.). But price isn't even a Wiener process, and yet it's still there.
This is a kindergarten, for God's sake. Cubes, bricks, balls and other geometric figures are randomly put together in the hope that the resulting structure will be stable.
Lately I have the impression, that all those classic indicators without a context of their use - is a purposeful propaganda and promotion of suckers. The less suckers think, the more money they can get. And then new ones will come. Circle of suckers in nature.
You know my attitude to this quest. And to the use of ANY indicators too.
But it's a good thing it was you who said it and not me (once again). I would probably have been required to confirm it with a statement. Or I would have been... shot.
===
Gentlemen. Don't hit hard, but! You're trying to look for a black cat in a dark room that isn't there. Or pulling a pair of francs over an octopus. Or... Confucius would have sufficed.
Think about the nature of the process in question and ask yourself a simple question: I, the Name-Broker, in my right mind and mind, really think that the historical price time series (RoC - not the point) can tell what the Bank of England or the US Federal Reserve will do, say? Or ML? Or GS? Not to mention such trivial things as statistics on consumption indices, unemployment, real estate, etc.
You remind me of the early Christians - Credo quia absurdum! Yes! It's appealing, it's romantic. But what does it have to do with real trade? If you're going to look for a model, it has to be through a neural network. But there is no sense in it either, because the reason does not lie in the time series. And therefore everything can change at any moment. Yes, a neural approach can reveal some logic in the actions of the big guy. But all the same - it is temporary.
In general, putting prediction of price as the basis of TS - the way to nowhere. You can simulate / predict the areas between the big guy's actions. But any big guy's action will kill all predictions. It's not the past time series that determines most of the strong moves in the market. All attempts (yours, others) have shown this well.
Why is the common perception that TA does not work? Because they try to predict the price. And the TA tools just capture a particular state of the market. They do not predict ANYTHING. That is not what they are for. A ruler cannot predict length. And a weight is not a weight. All this is analytics. And they are VERY valuable.
The predictive properties of TA can be used only locally for auxiliary, short term actions like entries/exits/reversals based on the logic of market sentiment determined by analysis. I say 'mood' because I'm already sick of the term 'context' myself.
I mean, if you're looking for it... - Anyway, I won't repeat myself.