[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: equity curve math ?



PureBytes Links

Trading Reference Links

Hello Chris,

There's a lot of discussion on the Sharpe Ratio on this list, so you
might visit http://www.purebytes.com/archives/omega/ for the
historical threads.

The rest is good old fashioned statistics.  You are trying to
mathematically characterize what you see with your own eyes when you
look at two equity curves.  You can draw a best fit line, and
calculate a standard error and establish a relationship between the
standard error and the slope of the best fit line, which is the
risk/reward ratio.  First calculate these values, then, combine the
trades of both to form a single equity curve, and then calculate the
best fit line, its slope and the standard error.  Compare this with
the sum of the values of the slope and SE of the two equity curves and
you have a correlation.

By the way, if the equity curves represent just 25 trades in the last
few months, then this is all pointless.


Monday, June 30, 2003, 7:45:16 PM, you wrote:


>> I want to find a measure to compare equity curves mathematically, i.e. how
>> straight they are, how close to best fit TL, etc. Anyone have any ideas?
>> It's been a long time since econometrics class. :-)
>>
>> Thanks,
>> Chris
>>