R: Rank Correlation for Censored Data

rcorr.cens {Hmisc}

R Documentation

Rank Correlation for Censored Data

Description

Computes the c index and the corresponding generalization of Somers' Dxy rank correlation for a censored response variable. Also works for uncensored and binary responses, although its use of all possible pairings makes it slow for this purpose.

Usage

rcorr.cens(x, S, outx=FALSE)

Arguments

`x`	a numeric predictor variable
`S`	an `Surv` object or a vector. If a vector, assumes that every observation is uncensored.
`outx`	set to `TRUE` to not count pairs of observations tied on `x` as a relevant pair. This results in a Goodman–Kruskal gamma type rank correlation.

Value

a vector with the following named elements: C Index, Dxy, S.D., n, missing, uncensored, Relevant Pairs, Concordant, Uncertain

Author(s)

Frank Harrell
Department of Biostatistics
Vanderbilt University
f.harrell@vanderbilt.edu

Examples

set.seed(1)
x <- round(rnorm(200))
y <- rnorm(200)
rcorr.cens(x, y, outx=TRUE)   # can correlate non-censored variables
if(.R.) library(survival)
age <- rnorm(400, 50, 10)
d.time <- rexp(400)
cens   <- runif(400,.5,2)
death  <- d.time <= cens
d.time <- pmin(d.time, cens)
rcorr.cens(age, Surv(d.time, death))

[Package Hmisc version 3.0-10 Index]