Thoughts on the random - page 15
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
Not only does it happen, but it happens in our world all the time.
You've written it all right, BUT.....
Instead of that you would do 1000 experiments in the hope of getting needed 50,5 - 51% in one of them, imagine that there are 1000 traders (they do not know about each other), each of which does ONE experiment. And now ONE of them has got 50.5 - 51% in his FIRST experiment. He looks at the result and says to himself - this can't be by chance, because it happened in the first experiment (he does not know about the others)!
I would agree if we are talking about +-50%. I wanted to get somewhere around 67-60% on a large sample. Didn't happen, sadly.
That's not all. I am well aware that I would have to demonstrate the reproducibility of this result. Let's say a controlled experiment,multiple times. The achievability of 6 sigma.
In probability theory, the infinite monkey theorem.)))))))))))))))))
We are all highly evolved primates.
My point is that even if the market is completely random, it is possible to make a series of deals with a sufficiently high success rate. The main thing is to get more monkeys))))
Personally, I think that quotes are a classic cocktail of deterministic and stochastic components.
We are all highly evolved primates.
Not true, some of us are still trying to get past the coacervate droplet stage.)
My point is that even if the market is completely random, it is possible to make a series of deals with a sufficiently high success rate. The main thing is to get more monkeys))))
Personally, I think that quotes are a classic cocktail of deterministic and stochastic components.
Logically, but the deterministic is still 'irradiated' by floating parameters, plus external influences themselves follow a random pattern (unless of course the market is exclusively driven by ZOG), and so the response will reflect that randomness.
In other words, randomness in quotes is not only additive (noise), which can be bluntly filtered out with one quality or another, but also fiercely multiplicative, embedded in both the market itself and the external environment.
1. Logically, but the deterministic is still "irradiated" by floating parameters, plus external influences themselves follow a random pattern (unless of course the market is exclusively driven by ZOG), hence the response will reflect that randomness.
2. In other words, randomness in quotes is not only additive (noise), which can be bluntly filtered out with one quality or another, but also fiercely multiplicative, embedded in both the market itself and the external environment.
1. I call it non-stationarity. If quotes were stationary, there would be nothing to talk about.
2. everything is crammed into the stochastic component
... "A cocktail of deterministic and stochastic components.
It is more accurate to speak of an evolutionary component rather than a deterministic one.
Logically, but deterministic is still "irradiated" by floating parameters, plus external influences themselves follow a random pattern (unless, of course, the market is exclusively driven by ZOG), and hence the response will reflect that randomness.
In other words, randomness in quotes is not only additive (noise), which can be bluntly filtered out with one quality or another, but also fiercely multiplicative, embedded in both the market itself and the external environment.
All this nerdiness fits perfectly into the additive model of signal+noise ;)
All this nonsense fits perfectly into the additive signal+noise model ;)
... only you won't know noise characteristics (unless you're a real mathematical genius), which means you won't be able to use standard methods (or more exactly, you won't get results), since they are 99% parametric, i.e. assume a particular variant of noise (BHP or derived from it). More precisely, it is possible to use them, but there is no way to assess their validity, i.e. whether the results are correct or not.
... Only you won't know the noise characteristics (unless you're a real math genius, of course), which means you won't be able to use standard methods (more exactly, you won't get the result), since they are 99% parametric, i.e. assume the particular variant of noise (GSR or derived from it). More precisely, it is possible to use them, but there is no way to assess their validity, i.e. whether the results are correct or not.
What noise characteristics do you need for trading purposes? There's no need to know the specific characteristics of noise. Well, maybe you want to determine these characteristics? Then the question may be relevant - why?
And notice that for some reason you don't raise the question, or even mention it, of signal characterisation. But it's the signal that counts. And noise is noise... ;)