.. ok, needed a bit and a second look. I was puzzled by the quality of the approach. It was too good to be true. While I did not get exactly what they are doing, they are clearly looking at all the data. So they are NOT doing a time series prediction. Any time series prediction approach cannot go so sharply from -1 to 1. If it would, it would also lead to a significant amplfication of any noise.
So, yes. This is a very interesting approach and paper. Perhaps it can be adapted and extended into a time-series prediction. But I do not see a direct relation to the question. Klaus On May 21, 8:43 am, Klaus <[email protected]> wrote: > Dear Nonlinear, > > this paper is indeed impressive. He also studies explicitly the > question how to approximate the > first derivative. The figures and result are extremely good.. > - what I did not get was the relation to double exponential > regression. > Is it hidden in some of the referenced approaches (I do not know?) > My impression was that the approach presented would be multiple orders > of magnitude more complex. > (though given the quality of the results, still a valid goal..) > > Cheers > Klaus > > On May 11, 11:43 pm, nonlinear <[email protected]> wrote: > > > > > > > > > On Wednesday, May 11, 2011 5:33:55 PM UTC-4, Alexana wrote: > > > > If you are looking for a bit of mathematical theory on this type of > > > methodology, take a look at the attached pdf. > > > ** > > > ... and > > this:http://math.lanl.gov/Research/Publications/Docs/chartrand-2010-numeri... -- 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.
