[R] Assistance with pointers to code for B-spline derivatives (S-plus related).

[Jeffrey Racine]

Hi.

I have been using the splines package for my work, in particular, the bs() function and associated predict() method. I now find myself in need of the derivatives of this beast.

In the man page for predict.bSpline I found `predict(object, x, nseg=50, deriv=0, ...)' but alas this is not implemented (deriv= is ignored). I contacted the package maintainers who were most helpful. Bill Venables kindly replied "Curiously, the S-PLUS code did have that feature, I recall, but as I no longer have S-PLUS I've lost contact with it.  If you know someone with S-PLUS and the splines code, you may be able to get somewhere with that."

Sadly, I do not have access to this code either. However, I was hoping that there is a large enough community of spline smoothers using R that perhaps they have written/adapted code that accomplishes what I need.

So, if you have any pointers as to how to generate derivatives for the bs() function in the splines package (or can point me to functionally equivalent code elsewhere that can return derivatives), I would be most grateful to hear from you.

Thanks in advance for your time.

-- Jeff


Professor J. S. Racine         Phone:  (905) 525 9140 x 23825
Department of Economics        FAX:    (905) 521-8232
McMaster University            e-mail: racinej at mcmaster.ca
1280 Main St. W.,Hamilton,     URL: http://www.economics.mcmaster.ca/racine/
Ontario, Canada. L8S 4M4

`The generation of random numbers is too important to be left to chance'