I have a further suggestion concerning the CPI measurement:

Suppose you have a strategy that shows a net profit P when run for 1 year 
and a net profit of 2P when run for 2 years.

Suppose the other measurements PI, Kelly are the same for both backtests.

In this case the CPI for 2 years is the double of the CPI for 1 year. As a 
quality measurement I think it should be identical for both cases.

In order to eliminate this problem one could simply exclude the term

* (netProfit / 1000)

from the formula (see my last post).

PI and Kelly (and in my case the added drawdown ratio), taken together as 
combined measurement of CPI, should be as performance index good enough for 
the moment.

What do you think, Eugene?

-- 
You received this message because you are subscribed to the Google Groups 
"JBookTrader" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/jbooktrader.
For more options, visit https://groups.google.com/groups/opt_out.

Reply via email to