mono.2d {monoProc}R Documentation

strictly monotone and smooth function

Description

this function applies a kernel smoothing method to monotonize a given fit with two independent variable

Usage

mono.2d(fit, bandwidth, xx, kernel = "epanech", dir = "xy", mono1, mono2)

Arguments

fit a list containing x-values and y-values as independent variables and their corresponding z-values. The length of fit[[1]] determines degree of acuteness of the monotonizing procedure
bandwidth a single number which represents the kernel bandwidth smoothing parameter. Missing values are not accepted.
xx an additional list of x-values and y-values where the monotonizing procedure is to be evaluated. If missing list(x=fit[[1]],y=fit[[2]]) is used instead.
kernel "`epanech"' - the Epanechnikov kernel
dir with respect to which variable and in which order the function is to be monotonized. Possible is "x", "y", "xy", and "yx"
mono1 either "increasing" or "decreasing" for x-variable
mono2 either "increasing" or "decreasing" for y-variable

Details

this function is used within "monoproc"

Value

returns an object of class "monofit"

Author(s)

Regine Scheder Regine.Scheder@rub.de

References

Dette, H., Neumeyer, N., and Pilz, K. (2004) A simple nonparametric estimator of a monotone regression function.

Dette, H. and Scheder, R. (2005) Striclty monotone and smooth nonparametric regression for two or more variable.

See Also

mono.1d and monoproc


[Package monoProc version 1.0-4 Index]