Random Flow Theory and FOREX - page 51

 
AlexEro >> :

I just don't know of "stationary" processes in mathematics. There are stationary RUNNING processes. What does this have to do with a tick price series that is generated by the meaningful activity of a group of disparate people looking at a graph and making decisions based on a target function that is communicated to them by their superiors? What does this have to do with randomness or stationary randomness?

While a crowd of disparate lemmings "making decisions" collectively creates a random process which is modelled by mathematical/statistical/probabilistic laws. Human behaviour has long been modelled mathematically in many areas of human activity, finance being just one of them.

 
timbo >> :

While a crowd of disparate lemmings "making decisions" collectively creates a random process which is modelled by mathematical/statistical/probabilistic laws. Human behaviour has long been modelled mathematically in many areas of human activity, finance being just one of them.

This is nonsense that is not in any scientific book - that a random process (that can withstand a randomness test, well at least by DieHard or the newfangled NIST package) is generated by living beings. This is just your invention, which you cannot not only prove, but even SHOW. So stop with the pseudo-scientific bullshit.

The opposite happens - it has already been mentioned and referenced here - Slutsky has shown (but not strictly proven) that a set of random variables MAY, sometimes may generate a process, which being smoothed by a sliding average, is similar to a time series of a living process (e.g. economic).

 
begemot61 писал(а) >>

Indeed... And where is such a book?

Enclosed. Peters. Chaos and Order in Capital Markets. Plenty in the public domain. One might not take such a harsh stance on the randomness of quotes, signal, noise, if it were not for the various Markovitzes out there, managed returns and risk, aimed at fooling investors in investment funds.

 
AlexEro писал(а) >>

This is nonsense, which cannot be found in any scientific book, that a random process (which can withstand a randomness test, at least by DieHard or the newfangled NIST package) can be generated by living beings. This is just your invention, which you cannot not only prove, but even SHOW. So stop with the pseudo-scientific bullshit.

The opposite happens - it has already been mentioned and referenced here - Slutsky shows (but not strictly proven) that a set of random variables MAY, sometimes may generate a process, which being smoothed by a moving average, is similar to a time series of a live process (e.g. economic).

Mass Service Theory. Every underground passenger randomly and independently enters the underground. For this random flow it is possible to calculate both queue length and waiting time quite accurately. But this is just a matter of speaking.

As has been shown in a number of papers, capital markets are non-linear dynamic systems with feedbacks (a memory of about 40 months). Most academics, and more importantly Nobel laureates, argue that such a precise market model is unnecessary, and can be limited to the model known as the efficient market hypothesis. What is there to discuss here? Who has fallen from what oak tree? Any constructive discussion presupposes that existing opinions and approaches are taken into account. Otherwise, it's just flub.

 
AlexEro >> :

This is nonsense, which cannot be found in any scientific book, that a random process (which can withstand a randomness test, at least by DieHard or the newfangled NIST package) can be generated by living beings. This is just your invention, which you cannot not only prove, but even SHOW. So stop with the pseudo-scientific bullshit.

Are you really so... advanced and theoretically savvy? Or are you just pretending so skillfully...?

Here's an example - https://en.wikipedia.org/wiki/Econometrics

All based on random processes, probabilities and statistics. I hope there is no doubt that economics is the result of living beings ("making decisions based on the objective function...").

 
faa1947 >> :

Mass Service Theory. Every underground passenger randomly and independently arrives at the underground. For this random flow, it is possible to calculate both queue lengths and waiting times quite accurately. But this is just a matter of speaking.

As has been shown in a number of papers, capital markets are non-linear dynamic systems with feedbacks (a memory of about 40 months). Most academics, and more importantly Nobel laureates, argue that such a precise market model is unnecessary, and can be limited to the model known as the efficient market hypothesis. What is there to discuss here? Who has fallen from what oak tree? Any constructive discussion presupposes that existing opinions and approaches are taken into account. Otherwise, it's just flooding.

See here about the adaptive market: http://web.mit.edu/alo/www/Papers/JPM2004.pdf


"...a new framework that reconciles market effciency with behavioural alternatives by applying the principles of
evolution competition, adaptation, and natural selection to financial interactions"

 
Choomazik >> :

No, not "it": https://en.wikipedia.org/wiki/Stationary_process. And for AlexEro, why don't you see if you feel lazy to google it?

In financial mathematics, "it's the same". I personally have never seen anyone bothering with strong stationarity, if the process is conventionally close to weak stationarity, then it's a blessing. Therefore, when saying stationary they usually mean weak stationarity.

 
Choomazik >> :

"...a new framework that reconciles market efficiency with behavioural alternatives by applying the principles of

evolution competition, adaptation, and natural selection to financial interactions"

There's a letter in that word! It's called the Behavioural Asset-Pricing Model. Built on the inconsistencies of CAPM. That is, as soon as they find a discrepancy in CAPM, they immediately say - and that's because BAPM. There are funny ideas, but that's all.

 
Choomazik писал(а) >>

see here about the adaptive market: http://web.mit.edu/alo/www/Papers/JPM2004.pdf

"...a new framework that reconciles market effciency with behavioural alternatives by applying the principles of
evolution competition, adaptation, and natural selection to financial interactions"

So, what's next?

 
timbo писал(а) >>

There is a letter in that word! It's called the Behavioural Asset-Pricing Model. It is based on the inconsistencies of CAPM. That is, when they find an inconsistency in CAPM, they immediately say - and that's because BAPM. There are funny ideas, but that's all.

It's not the BAPM and the inconsistencies of the CAPM. It's about the principle. Whether or not the expectation and variance change with time or position. If it does, can we ignore those changes. If we believe that the price will not slip through the stops, then maybe we can, but if we talk in theory, then we cannot, because it is impossible to predict crises in GER. Try explaining to unit holders the stationarity of a random flow of quotes when the price of a unit drops five times! It's nothing - the thick tails in the bell of the normal distribution are neglected.