R help - May 2008 - Optimal knot locations for splines

Suppose I have two variables, x and y.  For a fixed number of knots, I want
to create a spline transformation of x such that a loss function is
minimized.  Presumably, this loss function would be least squares, i.e. sum
(f(x)-y)^2.  The spline transformations would be linear, quadratic or
cubic.  I know I can solve this problem using some optimization function in
R, but I was wondering if anyone knew of a package that already solved this
problem.

I am conceving the solution as beginning with equidistant knot locations
based on the percentiles of x.  Then some routine would optimally shift
around the knot locations to minimize the loss function.

Mike

	[[alternative HTML version deleted]]

RSiteSearch('free knot splines', 'fun') produced 5 hits, the
first
of which is curfit.free.knot {DierckxSpline}. 

      RSiteSearch('estimate knots', 'fun') produced 54 hits, but
I don't
know if any of those would help you. 

      Spencer Graves

Mike Dugas wrote:
> Suppose I have two variables, x and y.  For a fixed number of knots, I want
> to create a spline transformation of x such that a loss function is
> minimized.  Presumably, this loss function would be least squares, i.e. sum
> (f(x)-y)^2.  The spline transformations would be linear, quadratic or
> cubic.  I know I can solve this problem using some optimization function in
> R, but I was wondering if anyone knew of a package that already solved this
> problem.
>
> I am conceving the solution as beginning with equidistant knot locations
> based on the percentiles of x.  Then some routine would optimally shift
> around the knot locations to minimize the loss function.
>
> Mike
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>