|
PureBytes Links
Trading Reference Links
|
Interesting. Could you explain this a little further. For instance what techniques are used? Can you share some references? Let's say you find that a series has some degree of complexity; some part
random, and some deterministic. Now what? Just because the series is found to be "not random" it would seem you'd have to determine what variables are important and I don't think any of the measures
you mentioned will do this. Correct?
Have you done any work using approximate entropy (ApEn) to measure randomness?
Reply privately is you'd like.
Regards,
Bill Vedder
rudolf stricker wrote:
> On Mon, 18 Dec 2000 20:50:03 -0600, you wrote:
>
> >This post brings up an interesting point (to me anyway); one that I've been grappling w/ for awhile. Simply, how does one know (most probably) whether his trading system results are random or not?
> >
>
> This imo primarily depends on the amount of randomness of the price /
> market data that are used. And for such "time series" there are well
> established analysis techniques to "measure" e.g. the "dimensionality"
> (of a representative attractor) of the (nonlinear) system behind these
> data. So we can get an impression of the "complexity" of the (market)
> system behind these data, even without having a valid model or even
> knowing the (most) relevant influence parameters.
>
> Of course there are limitations of these analysis methods, most often
> in terms of the restricted amount of data available, but practical
> results show, that there is a significant amount of determinism e.g.
> in option markets (, at least for the german DAX, which I have
> tested).
>
> mfg rudolf stricker
> | Disclaimer: The views of this user are strictly his own.
|