swh:1:snp:ff0951ca787d0b7f47dc2335f47fed43820a6324
Tip revision: 858421cbbaf89fbe446d88489ffe8534a90cb0f4 authored by Venkatraman E. Seshan on 20 November 2009, 00:00:00 UTC
version 0.8.7
version 0.8.7
Tip revision: 858421c
permtests.Rd
\name{permtests}
\title{Permutation versions of some common tests}
\alias{permtests}
\alias{permlogrank}
\alias{jonckheere.test}
\description{
Small sample tests using the permutation reference distributions.
}
\usage{
permlogrank(formula, data, subset, na.action, rho=0, nperm=5000)
jonckheere.test(x, g, alternative = c("two.sided", "increasing",
"decreasing"))
}
\arguments{
\item{nperm}{number of permutations for the reference distribution}
\item{formula, data, subset, na.action, rho}{see survdiff for details}
\item{x, g}{data and group vector}
\item{alternative}{means are monotonic (two.sided), increasing, or
decreasing}
}
\details{
permlogrank is the permutation version of k-sample survdiff
jonckheere.test is the exact (permutation) version of the
Jonckheere-Terpstra test. It uses the statistic
\deqn{\sum_{k<l} \sum_{ij} I(X_{ik} < X_{jl}) + 0.5 I(X_{ik} =
X_{jl}),} where \eqn{i, j} are observations in groups \eqn{k} and
\eqn{l} respectively. The asymptotic version is equivalent to
cor.test(x, g, method="k").
}
\keyword{htest}