|
PureBytes Links
Trading Reference Links
|
On Thu, 22 Oct 1998, Gary Funck wrote:
> Has any brave soul tried coding the cubic least squares fit mentioned
> in this month TASC, in Dennis Meyer's article? He references
> Numerical Recipes in C, and states that the exercise of coding
> this in EL is left to the reader ...
There was a good article on cubic spline interpolation in 'C Chest and
Other C Treasures from Dr. Dobb's Journal' 1987, isbn:0934375402. Not
likely to be found outside a university library.
>
> Anyone tried experimenting with cubic splines, or higher order
> polynomials as a way of getting a better handle on the trend?
>
A few years ago I used a progam called Curve which made a fit using higher
order polynomials. It would produce a great fit within the bounds of your
data set but would often blow up outside those bounds, i.e. you couldn't
extrapolate. If I can dig the disk up it might be interesting to see what
happens with a fit of some tick data.
Cheers,
Jim
|