smoother.fn: A smoother constructor function
In syhyunpark/csim: Constrained single index models (CSIM)

Description Usage Arguments Details Value See Also

Given both a vector of the current single index variable u = alpha'X and a vector of the treatment indicators Tr, smoother.fn constructs a set of B-spline smoother matrices, used in estimating the treatment-specific link functions (see fit.link.fn).

1 2	smoother.fn(Tr, u, nbasis.t = c(6, 6, 8), rho.grid = c(0, 0.25, 0.5), linear.link = FALSE)

`Tr`	treatment indicators, n-by-1 vector; each element represents one of the K available treatment options.
`u`	a vector of the current singe index variable, u = alpha'X.
`nbasis.t`	a length K+1 vector; each element specifies the number of B-spline basis funtions used in approximating the treatment-specific link function; the last element is for the "main effect" link function.
`rho.grid`	a grid vector of (ridge-type) smoothing parameters for approximating the link functions.
`linear.link`	if `TRUE`, restrict the link functions to be linear funtions; the default is `FALSE`.

The function returns a set of the QR decomposed design matrices (and the knot sequences used in constructing the B-spline design matrices), over the values of the (ridge-type) smoothing parameters, rho.grid. Since the ridge-type smoothing is equivalent to a regular least squares estimation with added observations, some psedo observations are added to the design matrices for the case of the nonzero values of rho.grid.

a list of information of the smoother matrices given the current single index variable including

`Bt.qr`	the QR decomposed design matrix constructed based on both the single index variable and the treatment indicator.
`B0.qr`	the QR decomposed design matrix based on the single index variable only.
`Bt`	the design matrix based on both the single index variable and the treatment indicator.
`B0`	the design matrix based on the single index variable only.
`knots.t`	the knot sequences used in constructing the treatment-specific B-spline design matrices.