swh:1:snp:f7f2912f5f954988ea730ec09e387c02a06b4418
Tip revision: 16f49417c4f7ce6308ba660aba56ee70319cd396 authored by Roger Koenker on 09 July 2020, 12:00:02 UTC
version 5.61
version 5.61
Tip revision: 16f4941
rq.fit.ppro.Rd
\name{rq.fit.ppro}
\alias{rq.fit.ppro}
\title{
Preprocessing fitting method for QR
}
\description{
Preprocessing method for fitting quantile regression models that
exploits the fact that adjacent tau's should have nearly the same
sign vectors for residuals.
}
\usage{
rq.fit.ppro(x, y, tau, weights = NULL, Mm.factor = 0.8, eps = 1e-06, ...)
}
\arguments{
\item{x}{
Design matrix
}
\item{y}{
Response vector
}
\item{tau}{
quantile vector of interest
}
\item{weights}{
case weights
}
\item{Mm.factor}{
constant determining initial sample size
}
\item{eps}{
Convergence tolerance
}
\item{\dots}{
Other arguments
}
}
\details{
See references for further details.
}
\value{
Returns a list with components:
\item{coefficients}{Matrix of coefficient estimates}
\item{residuals}{Matrix of residual estimates}
\item{rho}{vector of objective function values}
\item{weights}{vector of case weights}
}
\references{
Chernozhukov, V. I. Fernandez-Val and B. Melly,
Fast Algorithms for the Quantile Regression Process, 2019,
arXiv, 1909.05782,
Portnoy, S. and R. Koenker, The Gaussian Hare and the Laplacian
Tortoise, Statistical Science, (1997) 279-300
}
\author{
Blaise Melly and Roger Koenker
}
\seealso{
\code{\link{rq.fit.pfn}}, \code{\link{boot.rq.pxy}}
}
\keyword{regression}