|
PureBytes Links
Trading Reference Links
|
I read a review of some statistics packages (I think in Futures Mag)
recently and one of the features in 2 of the systems was "post hoc"
analysis. "post hoc" analysis is supposed to be able to take the set of
inputs and outputs to a system over a given period of time and give you an
estimation of whether your system's results are random chance or there is a
true correlation to the inputs and the outputs. I've put post hoc analysis
on my list of things to "look into", (right after I read the 18 books on
what makes a great trader, 33 books on developing systems, 15 books on
killer daytrading techniques, finish my system that generates AI/fuzzy
trading machines using genetic algorithms, write a decent market data
server, go back and get an MS in Math, read the 8 books on chaos in the
capital markets (although there might be 12 by the time I get to them), and
write a book on using chicken entrails and coffee grounds for EOD trading
(would you buy the title "So You've Got A Dead Chicken and A Futures
Account, Now What?")).
Anyway, anyone know more about post hoc analysis or use it to test viability
of their systems?
Kent
-----Original Message-----
From: Bilo Selhi <citadel@xxxxxxxxxxxx>
To: Omega List <omega-list@xxxxxxxxxx>
Date: Friday, June 30, 2000 5:36 PM
Subject: Why systems work and then don't work...
IMHO:
majority of the systems programmed out there are
RANDOM or close to it and what makes you
money is bias or we call it trend plus money management
if any.
entries and exits are mainly random.
what is a random system:
it's a system where the entries are random
no matter what timing technique used.
the parameters used in the system are optimized
to curve fit the bias/trend. this is usually results
in more/easier triggers for buy than
sell signals in up trend and vv. in down trend.
easier means conditions for buy are loosened
relative to the sells.
|