Monotonicity constraints for a cubic regression spline

Share:

Description

Finds linear constraints sufficient for monotonicity (and optionally upper and/or lower boundedness) of a cubic regression spline. The basis representation assumed is that given by the gam, "cr" basis: that is the spline has a set of knots, which have fixed x values, but the y values of which constitute the parameters of the spline.

Usage

1
mono.con(x,up=TRUE,lower=NA,upper=NA)

Arguments

x

The array of knot locations.

up

If TRUE then the constraints imply increase, if FALSE then decrease.

lower

This specifies the lower bound on the spline unless it is NA in which case no lower bound is imposed.

upper

This specifies the upper bound on the spline unless it is NA in which case no upper bound is imposed.

Details

Consider the natural cubic spline passing through the points (x_i,p_i), i=1..n. Then it is possible to find a relatively small set of linear constraints on p sufficient to ensure monotonicity (and bounds if required): Ap >= b. Details are given in Wood (1994).

Value

a list containing constraint matrix A and constraint vector b.

Author(s)

Simon N. Wood simon.wood@r-project.org

References

Gill, P.E., Murray, W. and Wright, M.H. (1981) Practical Optimization. Academic Press, London.

Wood, S.N. (1994) Monotonic smoothing splines fitted by cross validation. SIAM Journal on Scientific Computing 15(5), 1126–1133.

http://www.maths.bris.ac.uk/~sw15190/

See Also

magic, pcls

Examples

1
## see ?pcls

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.