mgcv. It is a service routine for
gam which splits of the strictly parametric part of the model formula and returns it as a formula and interprets the smooth parts
of the model formula.
The processing of
the smooth terms results in the return of the basis dimension for each smooth term, whether
or not the smooth term is to be treated as a pure regression spline
(i.e. one without a penalty) and the type of basis used to represent
the spline. It also returns an array of covariate names which are arguments of smooths, and the name of the response variable.
For further information on usuage see code for gam.Wood, S.N. (2000) Modelling and Smoothing Parameter Estimation with Multiple Quadratic Penalties. J.R.Statist.Soc.B 62(2):413-428
Wood, S.N. (2003) Thin plate regression splines. J.R.Statist.Soc.B 65(1):95-114
gam mgcv