| 1 |
% Generated by roxygen2: do not edit by hand |
| 2 |
% Please edit documentation in R/Cuminc.R |
| 3 |
\name{Cuminc} |
| 4 |
\alias{Cuminc} |
| 5 |
\alias{print.Cuminc} |
| 6 |
\title{Calculate nonparametric cumulative incidence functions and associated |
| 7 |
standard errors} |
| 8 |
\usage{ |
| 9 |
Cuminc(time, status, data, group, na.status = c("remove", "extra"), ...) |
| 10 |
} |
| 11 |
\arguments{ |
| 12 |
\item{time}{Either 1) a numeric vector containing the failure times or 2) a |
| 13 |
string containing the column name indicating these failure times} |
| 14 |
|
| 15 |
\item{status}{Either 1) a numeric, factor or character vector containing the |
| 16 |
failure codes or 2) a string containing the column name indicating these |
| 17 |
failure codes} |
| 18 |
|
| 19 |
\item{data}{When appropriate, a data frame containing \code{time}, |
| 20 |
\code{status} and/or \code{group} variables} |
| 21 |
|
| 22 |
\item{group}{Optionally, name of column in data indicating a grouping |
| 23 |
variable; cumulative incidence functions are calculated for each value or |
| 24 |
level of \code{group}. If missing no groups are considered} |
| 25 |
|
| 26 |
\item{na.status}{One of \code{"remove"} (default) or \code{"extra"}, |
| 27 |
indicating whether subjects with missing cause of failure should be removed |
| 28 |
or whether missing cause of failure should be treated as a separate cause of |
| 29 |
failure} |
| 30 |
|
| 31 |
\item{...}{Allows extra arguments for future extensions, but for now just |
| 32 |
used for backwards compatibility (e.g. allowing use of defunct \code{failcodes} |
| 33 |
argument in reverse dependencies).} |
| 34 |
} |
| 35 |
\value{ |
| 36 |
An object of class \code{"Cuminc"}, which is a data frame containing |
| 37 |
the estimated failure-free probabilities and cumulative incidences and their |
| 38 |
standard errors. The names of the dataframe are \code{time}, \code{Surv}, |
| 39 |
\code{seSurv}, and \code{cuminc} and \code{secuminc} followed by the values |
| 40 |
or levels of the \code{failcodes}. If \code{group} was specified, a |
| 41 |
\code{group} variable is included with the same name and values/levels as |
| 42 |
the original grouping variable, and with estimated cumulative incidences |
| 43 |
(SE) for each value/level of \code{group}. |
| 44 |
|
| 45 |
Cuminc is now simply a wrapper around survfit of the survival package with |
| 46 |
type=\code{"mstate"}, only maintained for backward compatibility. The |
| 47 |
survfit object is kept as attribute (\code{attr("survfit")}), and the print, |
| 48 |
plot and summary functions are simply print, plot and summary applied to the |
| 49 |
survfit object. Subsetting the \code{"Cuminc"} object results in subsetting |
| 50 |
the data frame, not in subsetting the survfit object. |
| 51 |
} |
| 52 |
\description{ |
| 53 |
This function computes nonparametric cumulative incidence functions and |
| 54 |
associated standard errors for each value of a group variable. |
| 55 |
} |
| 56 |
\details{ |
| 57 |
The estimated cumulative incidences are as described in Putter, Fiocco & |
| 58 |
Geskus (2007); the standard errors are the square roots of the Greenwood |
| 59 |
variance estimators, see eg. Andersen, Borgan, Gill & Keiding (1993), de |
| 60 |
Wreede, Fiocco & Putter (2009), and they correspond to the variances in eg. |
| 61 |
Marubini & Valsecchi (1995). In case of no censoring, the estimated |
| 62 |
cumulative incidences and variances reduce to simple binomial frequencies |
| 63 |
and their variances. |
| 64 |
} |
| 65 |
\examples{ |
| 66 |
|
| 67 |
### These data were used in Putter, Fiocco & Geskus (2007) |
| 68 |
data(aidssi) |
| 69 |
ci <- Cuminc(time=aidssi$time, status=aidssi$status) |
| 70 |
head(ci); tail(ci) |
| 71 |
ci <- Cuminc(time="time", status="status", data=aidssi, group="ccr5") |
| 72 |
head(ci); tail(ci) |
| 73 |
|
| 74 |
### Some fake data |
| 75 |
fake <- data.frame(surv=c(seq(2,10,by=2),seq(1,13,by=3),seq(1,9,by=2),seq(1,13,by=3)), |
| 76 |
stat=rep(0:3,5),Tstage=c(1:4,rep(1:4,rep(4,4)))) |
| 77 |
fake$stat[fake$stat==0 & fake$Tstage==2] <- 3 |
| 78 |
fake$stat[fake$stat==3 & fake$Tstage==1] <- 2 |
| 79 |
fake |
| 80 |
Cuminc(time="surv", status="stat", data=fake) |
| 81 |
# If we remove all entries with status=0, |
| 82 |
# we should get binomial sample probabilities and corresponding SEs |
| 83 |
fake0 <- fake[fake$stat!=0,] |
| 84 |
Cuminc(time="surv", status="stat", data=fake0) |
| 85 |
|
| 86 |
} |
| 87 |
\references{ |
| 88 |
Andersen PK, Borgan O, Gill RD, Keiding N (1993). |
| 89 |
\emph{Statistical Models Based on Counting Processes}. Springer, New York. |
| 90 |
|
| 91 |
Marubini E, Valsecchi MG (1995). \emph{Analysing Survival Data from Clinical |
| 92 |
Trials and Observational Studies}. Wiley, New York. |
| 93 |
|
| 94 |
Putter H, Fiocco M, Geskus RB (2007). Tutorial in biostatistics: Competing |
| 95 |
risks and multi-state models. \emph{Statistics in Medicine} \bold{26}, |
| 96 |
2389--2430. |
| 97 |
|
| 98 |
de Wreede L, Fiocco M, Putter H (2009). The mstate package for estimation |
| 99 |
and prediction in non- and semi-parametric multi-state models. Submitted. |
| 100 |
} |
| 101 |
\author{ |
| 102 |
Hein Putter \email{[email protected]} |
| 103 |
} |
| 104 |
\keyword{survival} |