|
PureBytes Links
Trading Reference Links
|
Kent wrote:
>Monte Carlo sims can be extrememly misleading with respect to drawdowns
>estimations.
I have to disagree here. If you scramble the order of trades
and calculate your return and drawdown for a thousand different
orderings, you can get an excellent idea of what the system can
give you in terms of minimum drawdown, maximum drawdown, average
drawdown, and standard devation of drawdowns. You can get the
same statistics for returns, as well as return/drawdown ratio.
In practice I have found you need only 300 or so trials for the
statistics to settle out.
I will agree that this sort of analysis doesn't let you adjust your
trading strategy in real time like you would if you traded only when
a hypothetical equity curve is above its moving average. But for
evaluating a system, it does give you a good idea of the range of
returns and drawdowns that you might reasonably expect.
--
,|___ Alex Matulich -- alex@xxxxxxxxxxxxxx
// +__> Director of Research and Development
// \
// __) Unicorn Research Corporation -- http://unicorn.us.com
|