** Next:** Some Special Spline Models
** Up:** General Smoothing Spline Regression
** Previous:** Model and Estimation

The S function for fitting a SSR model is `ssr`.
A typical call is

ssr(formula, rk, data)

Only the first two arguments, `formula` and `rk`, are
required. Together they describe the response variable and the model space.
`formula`, a statistical formula as in `lm`, lists the
response variable on the left hand side and the bases
of
on the right hand side of an operator `~`

.
`rk` is an expression that specifies the reproducing
kernel . Expressions of `rk` for commonly used
reproducing kernels are available in our library. These expressions
will be discussed in the following sections. Users can easily add
their own expressions of reproducing kernels.
The optional argument `data` specifies the data frame. Other
optional arguments will be discussed in the following sections.

`ssr` returns an object of class ``ssr'' with many variables
representing the fit to the specified smoothing spline model.
Detailed information about this object can be found in the help
file on `ssr.object`.

Yuedong Wang
2004-05-19