md.survnp {missDeaths} | R Documentation |
Nonparametric analysis of disease recurrence with missing information of possible deaths
Description
Estimates the Net and Event free survial using a is non-parametric approach
that aims to correct all individuals using the unconditional survival time
distribution obtained from the population mortality table.
The idea comes from realizing that the number of observed events in the data
equals the number which would be observed in case of a complete data set,
but the number of patients at risk does not. Hence, this method adjusts the
observed number at risk to mimic the one we would get if the data was
complete.
Usage
md.survnp(time, status, maxtime, D, ratetable, conf.int = 0.95)
Arguments
time |
the time to event (number of days) |
status |
the status indicator, 0=right censored, 1=event at |
maxtime |
maximum potential observation time (number of days). where where |
D |
demographic information compatible with |
ratetable |
a population mortality table, default is |
conf.int |
desired coverage of the estimated confidence interval |
Value
A list with components giving the estimates of net and event free survival.
time |
times where the estimates are calculated (number of days) |
Y.net |
adjusted number of patients at risk at each time in a hypothetical world where patients don't die |
Y.efs |
adjusted number of patients at risk at each time |
surv.net |
the estimated Net survival |
std.err.net |
the estimated standard error of Net survival estimates |
surv.efs |
the estimated Event free survival |
std.err.efs |
the estimated standard error of Event free survival estimates |
References
Stupnik T., Pohar Perme M. (2015) "Analysing disease recurrence with missing at risk information." Statistics in Medicine 35. p1130-43. https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.6766
Examples
## Not run:
library(missDeaths)
library(cmprsk)
data(slopop)
data(observed)
D = md.D(age=observed$age*365.2425, sex=observed$sex, year=(observed$year - 1970)*365.2425)
np = md.survnp(observed$time*365.2425, observed$status, observed$maxtime*365.2425, D, slopop)
#calculate net survival at 3 and 9 years
w = list(list(time=np$time, est=np$surv.net, var=(np$std.err.net)^2))
timepoints(w, times=c(3,9)*365.2425)
#plot the net and event free survival curves
plot(np$time, np$surv.net)
plot(np$time, np$surv.efs)
## End(Not run)