|
PureBytes Links
Trading Reference Links
|
Walter,
Thanks for some nice references over the last couple of weeks.
This is a very interesting paper... I find their claim
counterintuitive, but I'll code up a coin toss program and
see for myself I suppose.
Since you have are into mathematical modeling, take a look
at Lester Ingber's "Canonical Momentum Indicators" (CMI)
try http://www.ingber.com (then click on "MARKETS")
I have a very strong mathematical background, but Lester's
stuff is generally over my head. Maybe you can make sense
of it. I know CMI has worked very well for him in both
options and futures trading. From what little I understand of
it, there is no reason it could not be applied to any market.
If you can understand it, maybe you can enlighten the rest of us.
By the way, what is the BF list?
Jeff
In metastock, Walter Lake (wlake@xxxxxxxxx) wrote:
>Thanks for your emails
>
>This appeared a while back on the BF list. It will probably be of interest
>in developing your trading system to take advantage of it..
>
>Watch out for those "xxx" sites <G>
>
>Best regards
>
>Walter
>
>> Let me report some recent discussions at yats@xxxxxxxxxxx
>> Alex Plank mentioned a very interesting article from Sornette
>> (http://xxx.lpthe.jussieu.fr/abs/cond-mat/0001324)
>>
>> "We present a simple and general result that the sign of the
>variations or
>> increments of uncorrelated times series are predictable with a
>remarkably
>> high success probability of 75% for symmetric sign distributions.
>The origin
>> of this paradoxical result is explained in details. We also present
>some
>> tests on synthetic, financial and global temperature time series. "
>>
>> We had some difficulties in understanding the trick, and some have
>built
>> successful trading model form this ;-)
>>
>> In subsatnce this article told us that the price return are
>oscillating
>> around its mean. If the yesterday return is heigher than its mean
>we can
>> predit that today return will be lower than yesterday return, and
>vice
>> versa, with a 75% success rate.
>>
>> I suspect that many chartist patterns are victims of this,
>including Elliott
>> Wave, Fibonacci, and generaly speaking, all pull-back based
>patterns,
>>
>> Some kind of optical illusions that provide any edge, since the
>basis of
>> those patterns is market efficiency !!!
>>
>
>
|