Minimum drawdawn is preferred to max drawdawn. Strategy A is better in my
opinion as it proves it can recover from drawdowns repeatedly
On Jun 20, 2011 9:10 AM, "nonlinear" <[email protected]> wrote:
> There is another, more subtle problem with the max DD measure, which is
that
> by reshuffling the same trades of the same strategy you would get
> drastically different max DD figures. It's as though the same strategy
> suddenly changes from "good" to "bad" by simply rearranging the trades in
> time. In reality, it's still exactly the same strategy, with exactly the
> same risk/reward profile.
>
> If this doesn't click in, think about this experiment. You have two coins,
A
> and B, and you suspect that one of them is a fair coin, while the other
one
> is a loaded one. So, you flip each one 1 million times. The results are:
> 500,000 heads and 500,000 tails for each coin. However coin A had a a
> maximum streak of 10 heads in a row, while coin B had a maximum of 5 heads

> in a row. Based on the Sterling Ratio adapted for coins, coin B would be
> determined to be 2 times more "fair" than coin A, when in reality, both
> coins are perfectly and equally fair. On the other hand, if you use the PI

> measure, it would be identical for coins A and B.
>
>
> --
> You received this message because you are subscribed to the Google Groups
"JBookTrader" group.
> To view this discussion on the web visit
https://groups.google.com/d/msg/jbooktrader/-/svCLzimFb1gJ.
> To post to this group, send email to [email protected].
> To unsubscribe from this group, send email to
[email protected].
> For more options, visit this group at
http://groups.google.com/group/jbooktrader?hl=en.
>

-- 
You received this message because you are subscribed to the Google Groups 
"JBookTrader" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/jbooktrader?hl=en.

Reply via email to