In my particular case below, the values of the objective function are completely different as well. The one related to 18% CAR is good and the one related to 4% is bad, which does not correspond to your last sentence. What conclusion do you make on this? My conclusion is that CMAE did not find the maximum the second time.
--- In [email protected], Howard B <howardba...@...> wrote: > > Hi Z -- > > Ton is making the correct suggestion. > > CMAE uses method that are non-exhaustive -- that is, they do not test every > possible combination of the variables being optimized. As a result, CMAE > may find different local maxima rather than the global maximum. An > exhaustive optimization will find the global maximum within the space being > searched. If there are two or more maxima with the same objective function > value (which is very unlikely), then the parameters could be different, but > the objective function values will be the same. > > Thanks, > Howard > > > On Sun, Oct 11, 2009 at 1:22 PM, zozuzoza <zoz...@...> wrote: > > > > > > > I found an interesting behavior of WF testing in Amibroker. Using the same > > AFL code, same parameters, same environment, same fitness function, > > everything is the same, but the results are completely different when I run > > it second time. I say completely, i.e. good WF results turned weak when I > > run it the 2nd time the WF test. I did not expect to have the same results > > due to the nature of non exhaustive optimiser but the results I got > > eliminated my faith in Amibroker WF usefulness. I used cmae optimiser. > > > > Running 2 times the WF test turned the average CAR of 18% to 4% the second > > time I run. There were about 50 trades in the IS period. > > > > Try it yourself! > > > > > > >
