bda (version 3.2.0-3)

npr: non-parametric regression

Description

To fit nonparametric regression model.

Usage

npr(y,x, bw, sd.y, from, to, gridsize,conf.level=0.95)

Arguments

y,x

Two numerical vectors.

from,to,gridsize

start point, end point and size of a fine grid where the EDF will be evaluated.

bw

Smoothing parameter. Numeric or character value is allowed. If missing, adaptive (LSCV) bandwidth selector will be used.

sd.y

Standard deviation of y.

conf.level

Confidence level.

Examples

x <- rnorm(100,34.5,1.5)
 e <- rnorm(100,0,2)
 y <- (x-32)^2 + e
 out <- npr(y,x)
 out
 plot(out, type='l', scb=TRUE)
 x0 <- seq(min(x),max(x),length=100)
 y0 <- (x0-32)^2
 lines(x0, y0, col=2)
 points(x, y, pch="*", col=4)