lprq2: Local Linear Regression Methods for Conditional Quantile...

In Rearrangement: Monotonize Point and Interval Functional Estimates by Rearrangement

Description

Implements the local nonparametric method, local linear regression estimator with box kernel (default), for conditional quantile functions. This is a modification of Koenker's lprq ( from package quantreg).

Usage

lprq2(x, y, h, xx, tau)

Arguments

x	The conditioning covariate
y	The response variable
h	The bandwidth parameter
xx	The points at which the function is to be estimated
tau	The quantile(s) to be estimated. This should be a list of quantiles if the function estimates the quantile process

Details

The function uses a box kernel.

Value

xx	The design points at which the evaluation occurs
fitted.values	The estimated function values at these design points

Author(s)

Wesley Graybill, Mingli Chen, Victor Chernozhukov, Ivan Fernandez-Val, Alfred Galichon

Examples

require(quantreg)
data(GrowthChart)
attach(GrowthChart)

ages <- unique(sort(age))
llq.fit1 <- lprq2(age,height,h=1,xx=ages,tau=0.2)
detach(GrowthChart)

Rearrangement documentation built on May 1, 2019, 11:29 p.m.