Eugene.... If jchart supports 3d charts that would be perfect. So we
have 3d surface to look at. Also what I use at work a lot is parallel
coordinates plot to visualize ndimensional data

On Aug 13, 1:39 pm, nonlinear5 <[email protected]> wrote:
> > For instance, changing one parameter by 10 might be "equivelent" to changing
> > another parameter by 20.  I don't even know how you would quantify the
> > "range" except for the cases where you can determine the full range in which
> > the parameter applies (i.e. the range in which a certain parameter can be
> > that will generate at least N trades).
>
> In the first implementation of the new robustness metric, I would
> define the range as simply plus/minus 10% of the parameter value. So,
> for a parameter set {10, 100}, the "neighbors" would be in {9..11,
> 90..110}. I agree with you that this may be too primitive, but we can
> improve it later.
>
> > Furthermore, you simply cannot judge performance with a number.   Surface
> > plots are a must.  My main beef with the JBT plots is that you only get to
> > see the "best" and "worst" strategies for a range of 2 variables.   It would
> > be infinitely more valuable to look at a plot of X vs Y while Z=30 and
> > Q=40.
>
> This should not be very difficult. I'll take a look at that.
>
> > Which brings me to my last point:  you really need to cut down the number of
> > parameters if you have more than 4.  I find 4 to be too much.  
>
> I agree.
--~--~---------~--~----~------------~-------~--~----~
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