bsplines: B-spline bases
In kidusasfaw/pomp: Statistical Inference for Partially Observed Markov Processes

Description Usage Arguments Value C API Author(s) Examples

These functions generate B-spline basis functions. bspline.basis gives a basis of spline functions. periodic.bspline.basis gives a basis of periodic spline functions.

bspline.basis(x, nbasis, degree = 3, deriv = 0, names = NULL)

periodic.bspline.basis(x, nbasis, degree = 3, period = 1, deriv = 0,
  names = NULL)

`x`	Vector at which the spline functions are to be evaluated.
`nbasis`	The number of basis functions to return.
`degree`	Degree of requested B-splines.
`deriv`	The order of the derivative required.
`names`	optional; the names to be given to the basis functions. These will be the column-names of the matrix returned. If the names are specified as a format string (e.g., "basis%d"), `sprintf` will be used to generate the names from the column number. If a single non-format string is specified, the names will be generated by `paste`-ing `name` to the column number. One can also specify each column name explicitly by giving a length-`nbasis` string vector. By default, no column-names are given.
`period`	The period of the requested periodic B-splines.

`bspline.basis`	Returns a matrix with `length(x)` rows and `nbasis` columns. Each column contains the values one of the spline basis functions.
`periodic.bspline.basis`	Returns a matrix with `length(x)` rows and `nbasis` columns. The basis functions returned are periodic with period `period`.

If deriv>0, the derivative of that order of each of the corresponding spline basis functions are returned.

Access to the underlying C routines is available: see the header file ‘pomp.h’ for definition and documentation of the C API. At an prompt, execute

1	file.show(system.file("include/pomp.h",package="pomp2"))

to view this file.

Aaron A. King

x <- seq(0,2,by=0.01)
y <- bspline.basis(x,degree=3,nbasis=9,names="basis")
matplot(x,y,type='l',ylim=c(0,1.1))
lines(x,apply(y,1,sum),lwd=2)

x <- seq(-1,2,by=0.01)
y <- periodic.bspline.basis(x,nbasis=5,names="spline%d")
matplot(x,y,type='l')