Estimation of the median potential followup time.

The reverse Kaplan-Meier method estimates the median potential followup time.

followup(formula, cens.code = 0, data, ...)

Arguments

formula

A formula whose left hand side is a Hist or a Surv object specifying the event time and the event type where by default 0=censored, 1=event, 2=competing risk (if any). Use cens.code to change the value for censored.

cens.code

Value of the event

data

A data.frame in which all the variables of formula can be interpreted.

...

Arguments passed to prodlim.quantile.

Value

The estimated median potential followup time with inter quartile ranges.

Details

This is merely a wrapper for prodlim with argument reverse.

References

Michael Schemper and Terry L. Smith. A note on quantifying follow-up in studies of failure time. Controlled Clinical Trials, 17(4):343–346, 1996.

See also

prodlim

Author

Thomas A. Gerds <tag@biostat.ku.dk>

Examples

set.seed(8)
d <- SimCompRisk(117)

# overall
followup(Hist(time,event)~1,data=d)
#> Median and inter quartile range (IQR) of the potential follow up time based on the reverse Kaplan-Meier method.
#> Key: <X>
#>          X      Median (IQR)
#>     <char>            <char>
#> 1: Overall 8.22 (4.61;11.46)

# in strata defined by variable X1 
followup(Hist(time,event)~X1,data=d)
#> Median and inter quartile range (IQR) of the potential follow up time based on the reverse Kaplan-Meier method.
#> Key: <X1>
#>       X1      Median (IQR)
#>    <num>            <char>
#> 1:     0    8.42 (7.65;--)
#> 2:     1 7.35 (4.04;10.12)