|
PureBytes Links
Trading Reference Links
|
the distribution of these numbers.
a pair of good looking $gain and %gain could have a
real ugly distribution like a fat tail on the losing side, which
implies you will have high probability taking hugh losses in the future.
-Lawrence Chan
>
> > #2 - $ gain averages or % gain averages are not dependable
> > measures of a good system. It just show how the system's been
> > curve fit (all backtesting are some form of curve fit) to the historical
> > data without appropriate understanding of the properties of the
> > price stream to be traded. Thus trading system with just $ gain
> > or % gain numbers looking ok is committing suicide.
>
> But these two numbers together ($Gain & %Win), along with $Loss, give you
> the mathematical expectancy of the system, which would seem to be fairly
> important.
>
> If not these numbers, then what do you use, Lawrence, to evaluate your
> trading system results? Since you have a strong background in statistics,
do
> you use confidence intervals & the like, Monte Carlo simulations, etc?
>
> Thanks,
>
> Cab Vinton
>
>
>
>
|