|
PureBytes Links
Trading Reference Links
|
I guess if you really disliked having these anomalously large profits in your
100 or so trades per year, you could always give the profits on those trades
back to the broker when they happen. So as not to sully the statistical purity
of your results, of course.
Jim Allen
Mark Brown wrote:
> > Remember the thread earlier this month where people thought you should
> throw out the extraordinarily large gains when assessing a system's
> performance? I don't think you should. Those are the elephants you're
> hunting. If they never occur, you've got a system/tradable with no real
> upside potential.
> >
> > John
>
> John, I can no speak for others but I wish to make my point on this
> subject.
>
> 1.) If you are a position trader who makes 5-15 trades a year following a
> "TREND" method. One probably should not throw out the big winning trades I
> would agree. After all that is what the system is designed to do. However
> I dislike these types of systems for many more reasons than I have time to
> discuss.
>
> 2.) If you have a system that trades perhaps 50 to 125 trades a year and
> these average trades are dependable in size. Then what I have done is to
> discount the few extraordinary winning trades by about 25%. There are few
> of them and so I don't want to become dependent on thinking they will always
> be there like a "TREND" follower. In fact I had much rather see if the
> model will hold up without any huge anomaly winning trades, then when I do
> get them we order cheesecake!
>
> Mark Brown
|