|
PureBytes Links
Trading Reference Links
|
DT,
Yes, I too have looked into the FFT. You are right, the Fast Forier
Transform does try to "predict" by by identifying the predominant
wave amplitude and duration. Ehlers uses other versions as well
as his own modifications and filters. His waveform studies are truly
impressive. Having said that, I have yet to see Transform system give
any better results than a good indicator based system submitted by
people like yourself and others.
If we look at Ehlers articles in S&C mag. over the past couple of
years, his highly complicated systems don't seem to be any more
accurate than a well constructed conventional indicator system.
(I base this comment on the buy/sell signals and trade results
published in these same articles)
Even when a Transform identifies the predominant waveform, we still
don't know if the next developing trend will conform to this
waveform. It may just be a small blip which conforms to one of the
many minor waves (of different timeframe)which are also part of the
same data set. Once again, a gamble of probability.
I know....I keep coming back to that word...."Probability".
I'm beginning to think that studies in math probability are the
way to go. Assigning prabability ratings to various outcomes based on
the "setup" of Volume, Gaps, price runs, etc..from the previous
day(s). DT, any thoughts or experience with that theory ?
Cheers,
gosub
Hey, you guys on the plunge protection team....
leave the NASDAQ alone....let it fall !
--- In amibroker@xxxxxxxxxxxxxxx, "DIMITRIS TSOKAKIS" <TSOKAKIS@xxxx>
wrote:
> There is also a recent [interesting] discussion at
> http://forum.esignalcentral.com/showthread.php?
> s=a2b3dcf4416e6a5431d6d44c605b0050&threadid=436&pagenumber=1
> DT
------------------------ Yahoo! Groups Sponsor ---------------------~-->
Your own Online Store Selling our Overstock.
http://us.click.yahoo.com/rZll0B/4ftFAA/46VHAA/GHeqlB/TM
---------------------------------------------------------------------~->
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
|