I don't rely much on out-of-sample backtesting. Rather, I optimize over the recent period (like the last 6 months or so), and trade live what I believe to be superior strategies.
On Tue, Mar 15, 2011 at 12:32 PM, Klaus <[email protected]>wrote: > Dear Nonlinear, > > did you also retest outside the scope of the training set? > I finally got around on the weekend doing this, but while I got > improvement over the training set, > I did not get very much improvement outside the training set.. > > Klaus > > > On Mar 14, 7:54 pm, nonlinear <[email protected]> wrote: > > > I think, it is perfectly right to differentiate between up- and > > > downward trends. > > > By and large downward seems in general much faster. > > > This would speak for a difference in parameters. > > > I always wanted to look at what happens if you do separately optimize > > > a upward-only > > > and a downward-only strategy and compose it later (going flat if both > > > are opposing) > > > and compare this with two-sided optimization. > > > > I separated my log-short strategies into long-only and short-only, and > > reoptimized. Got a big boost on all performance metrics. Don't know why > this > > idea never occurred to me in the past several years that I spent on > strategy > > design. > > -- > 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. > > -- 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.
