swh:1:snp:16c54c84bc54885e783d4424d714e5cc82f479a1
Tip revision: d90516ef8fb8d7c848eb685f443359b2a267a100 authored by Roger Koenker on 18 September 2004, 00:00:00 UTC
version 3.52
version 3.52
Tip revision: d90516e
ranks.rd
\name{ranks}
\alias{ranks}
\title{
Quantile Regression Ranks
}
\description{
Function to compute ranks from the dual (regression rankscore) process.
}
\usage{
ranks(v, score="wilcoxon", tau=0.5)
}
\arguments{
\item{v}{
object of class \code{"rq.process"} generated by \code{rq()}
}
\item{score}{
The score function desired. Currently implemented score functions
are \code{"wilcoxon"}, \code{"normal"}, and \code{"sign"}
which are asymptotically optimal for
the logistic, Gaussian and Laplace location shift models respectively.
The "normal" score function is also sometimes called van der Waerden scores.
Also implemented are the \code{"tau"} which generalizes sign scores to an
arbitrary quantile, and \code{"interquartile"} which is appropriate
for tests of scale shift.
}
\item{tau}{
the optional value of \code{tau} if the \code{"tau"} score function is used.
}}
\value{
The function returns two components. One is the ranks, the
other is a scale factor which is the \eqn{L_2} norm of the score
function. All score functions should be normalized to have mean zero.
}
\details{
See GJKP(1993) for further details.
}
\references{
Gutenbrunner, C., J. Jureckova, Koenker, R. and Portnoy,
S. (1993) Tests of linear hypotheses based on regression
rank scores, \emph{Journal of Nonparametric Statistics}, (2), 307--331.
}
\seealso{
\code{\link{rq}}, \code{\link{rq.test.rank}} \code{\link{anova.rq}}
}
\examples{
data(stackloss)
ranks(rq(stack.loss ~ stack.x, tau=-1))
}
\keyword{regression}
% Converted by Sd2Rd version 0.3-3.