summary.survfit: Summary of a Survival Curve

View source: R/summary.survfit.R

summary.survfitR Documentation

Summary of a Survival Curve

Description

Returns a list containing the survival curve, confidence limits for the curve, and other information.

Usage

  ## S3 method for class 'survfit'
summary(object, times, censored=FALSE, scale=1,
  extend=FALSE, rmean=getOption('survfit.rmean'), data.frame=FALSE, dosum, ...)
  ## S3 method for class 'survfitms'
summary(object, times, censored=FALSE, scale=1,
  extend=FALSE, rmean=getOption('survfit.rmean'), data.frame=FALSE, ...)
  

Arguments

object

the result of a call to the survfit function.

times

vector of times; the returned matrix will contain 1 row for each time. The vector will be sorted into increasing order; missing values are not allowed. If censored=T, the default times vector contains all the unique times in fit, otherwise the default times vector uses only the event (death) times.

censored

logical value: should the censoring times be included in the output? This is ignored if the times argument is present.

scale

numeric value to rescale the survival time, e.g., if the input data to survfit were in days, scale = 365.25 would scale the output to years.

extend

logical value: if TRUE, prints information for all specified times, even if there are no subjects left at the end of the specified times. This is only used if the times argument is present.

rmean

Show restricted mean: see print.survfit for details

data.frame

if TRUE, return the results as a data frame, rather than a summary.survfit object

dosum

only applicable if times is present, see details below

...

for future methods

Value

if data.frame = TRUE, a data frame with columns of time, n.risk, n.event, n.censor, surv, cumhaz, strata (if present) and data (the row of newdata for survfit.coxph). Also std.err, std.chaz, upper and lower if the curve had se.fit=TRUE.

if data.frame = FALSE, a list with the following components:

surv

the estimate of survival at time t+0.

time

the timepoints on the curve.

n.risk

the number of subjects at risk at time t-0 (but see the comments on weights in the survfit help file).

n.event

if the times argument is missing, then this column is the number of events that occurred at time t. Otherwise, it is the cumulative number of events that have occurred since the last time listed until time t+0.

n.entered

This is present only for counting process survival data. If the times argument is missing, this column is the number of subjects that entered at time t. Otherwise, it is the cumulative number of subjects that have entered since the last time listed until time t.

n.exit.censored

if the times argument is missing, this column is the number of subjects that left without an event at time t. Otherwise, it is the cumulative number of subjects that have left without an event since the last time listed until time t+0. This is only present for counting process survival data.

std.err

the standard error of the survival value.

conf.int

level of confidence for the confidence intervals of survival.

lower

lower confidence limits for the curve.

upper

upper confidence limits for the curve.

strata

indicates stratification of curve estimation. If strata is not NULL, there are multiple curves in the result and the surv, time, n.risk, etc. vectors will contain multiple curves, pasted end to end. The levels of strata (a factor) are the labels for the curves.

call

the statement used to create the fit object.

na.action

same as for fit, if present.

table

table of information that is returned from print.survfit function.

type

type of data censoring. Passed through from the fit object.

Details

This routine has two uses: printing out a survival curve at specified time points (often yearly), or extracting the values at specified time points for further processing. In the first case we normally want extend=FALSE, i.e., don't print out data past the end of the curve. If the times option only contains values beyond the last point in the curve then there is nothing to print and an error message will result. For the second usage we often want extend=TRUE, so that the results will have a predictable length. If data.frame = TRUE then either might be desired.

For a printout at fixed times, for example yearly values for a curve, the printed number of events will by default be the total number of events that have occured since the prior line of printout, and likewise for number of censored and number at entry, dosum = TRUE. Alternately, the routine can return the number of events/censors/entry at that time, dosum=FALSE. The default for dosum is TRUE if the times vector is strictly increasing and FALSE otherwise.

For a survfitms object replace the surv component with pstate. Also, a data frame will not include the cumulative hazard since it has a different multiplicity: one column per transition rather than one per state.

The survfit object itself will have a row of information at each censoring or event time, the default is not save information on each unique entry time. For printout at two time points t1, t2, this function will give the the number at risk at the smallest event times that are >= t1 and >= t2, respectively, the survival curve at the largest recorded times <= t1 and <= t2, and the number of events and censorings in the interval t1 < t <= t2.

When the routine is called with counting process data many users are confused by counts that are too large. For example, Surv(c(0,0, 5, 5), c(2, 3, 8, 10), c(1, 0, 1, 0)) followed by a request for the values at time 4. The survfit object has entries only at times 2, 3, 8, and 10; there are 2 subjects at risk at time 8, so that is what will be printed.

See Also

survfit, print.summary.survfit

Examples

summary( survfit( Surv(futime, fustat)~1, data=ovarian))
summary( survfit( Surv(futime, fustat)~rx, data=ovarian))

survival documentation built on June 22, 2024, 10:49 a.m.