Revision 50717074f4f077d9d345caf3f6ba6dc7a025fd79 authored by Roger Koenker on 28 June 2019, 14:00:07 UTC, committed by cran-robot on 28 June 2019, 14:00:07 UTC
1 parent d55e8b3
rq.fit.pfn.Rd
\name{rq.fit.pfn}
\alias{rq.fit.pfn}
\title{ Preprocessing Algorithm for Quantile Regression}
\description{
A preprocessing algorithm for the Frisch Newton algorithm
for quantile regression. This is one possible method for rq().}
\usage{
rq.fit.pfn(x, y, tau=0.5, Mm.factor=0.8, max.bad.fixup=3, eps=1e-06)
}
\arguments{
\item{x}{design matrix usually supplied via rq() }
\item{y}{ response vector usually supplied via rq() }
\item{tau}{ quantile of interest }
\item{Mm.factor}{ constant to determine sub sample size m}
\item{max.bad.fixup}{ number of allowed mispredicted signs of residuals }
\item{eps}{ convergence tolerance }
}
\details{
Preprocessing algorithm to reduce the effective sample size for QR
problems with (plausibly) iid samples. The preprocessing relies
on subsampling of the original data, so situations in which the
observations are not plausibly iid, are likely to cause problems.
The tolerance eps may be relaxed somewhat.
}
\value{
Returns an object of type rq
}
\references{ Portnoy and Koenker, Statistical Science, (1997) 279-300}
\author{ Roger Koenker <rkoenker@uiuc.edu>}
\seealso{ \code{\link{rq}}}
\keyword{ regression }
Computing file changes ...