by: H.J. Woltring, University of Nijmegen, Philips Medical Systems, Eindhoven (The Netherlands)
Natural B-spline data smoothing subroutine, using the Generalized Cross-
Validation and Mean-Squared Prediction Error Criteria of Craven & Wahba
(1979). Alternatively, the amount of smoothing can be given explicitly, or
it can be based on the effective number of degrees of freedom in the
smoothing process as defined by Wahba (1980). The model assumes
uncorrelated, additive noise and essentially smooth, underlying functions.
The noise may be non-stationary, and the independent co-ordinates may be
spaced non-equidistantly. Multiple datasets, with common independent
variables and weight factors are accomodated. A full description of the
package is provided in: H.J. Woltring (1986), A FORTRAN package for
generalized, cross-validatory spline smoothing and differentiation.
Advances in Engineering Software 8(2):104-113