|
PureBytes Links
Trading Reference Links
|
At 11:59 AM +0100 9/9/02, mark.keenan@xxxxxxxxxxxxxx wrote:
>If for example I optimise a set of parameters over 2000 days of trading and
>get a near a near linear equity curve - then the same parameters that work
>over the first 1000 days should work equally well over the next 1000 days
>as well.
True.
>Therefore is it true to say that most important thing to look for in
>optimizing in sample data would be a linear equity curve rather than net
>profit or profit factors and then apply these optimized parameters to the
>out of sample data.
True. A linear equity curve means a low standard deviation of returns
which means a high Sharpe Ratio. So look for a linear equity curve =
a high Sharpe Ratio.
>In addition - do you think a system should be optimized with money
>management orders in place, or should they be added after the most optimum
>inputs are identified???
If you are referring to scaling the trade size with account size
(such as fixed fractional), in that case the ideal equity curve is an
exponentially increasing one so you would like the logarithm of the
equity curve to be linear.
It is easier to do the optimizations with a "fixed trade size" and
aim for a linear equity curve, then add scale-trading later.
By "fixed trade size", I do not necessarily mean a constant number of
contracts. It could mean a fixed risk level or a fixed number of
dollars of equity controlled, or a fixed number of contract, etc.,
depending upon how your system works.
Bob Fulks
|