PureBytes Links
Trading Reference Links
|
thanks for the stats knowledge.
will check your site..
----- Original Message -----
Sent: Saturday, February 26, 2005 8:57
AM
Subject: [EquisMetaStock Group] Re:
Ergodic Theory
Hi,
Ergodicity is a property, not an
indicator. If something is ergodic, then it means (generally) the
thing is stable and converges in the long term. To give an example,
say every day you observe the returns on the Dow. If it is on average
say 1% and, as you add more and more and infinitely more days, it stays at
1% and the variance of this estimate goes to zero, then it is
ergodic. No matter what happens, the market (soon) returns to its 1%
average. If this 1% estimate changes as more days are added, even
slightly, then the market is not ergodic.
So I guess an ergodic
indicator would eventually settle on some long term average and never
deviate from it, otherwise you know it is not an ergodic
indicator!
I think markets are not likely to be ergodic......
Ergodicity requires something called covariance stationarity which means
that the market always behaves in a certain pattern at all times,
sans noise, dictated by what happened during the past couple of days
and the distant past dying out. There are way too many outliers,
too much noise, things like volatility clustering and
stochastic volatility that are not ergodic.
Regards MG
Ferreira TsaTsa EOD Programmer and trading model builder http://tsatsaeod.ferra4models.com http://www.ferra4models.com
---
In equismetastock@xxxxxxxxxxxxxxx, "lynn14344" <darisr@xxxx>
wrote: > > Hi Everyone, > > Can someone please help
me to create an indicator for ergodic. > > Please, please
someone assist me. > > Thank you very
much
Yahoo! Groups Sponsor |
ADVERTISEMENT
| |
|
Yahoo! Groups Links
|
|