td.sens.spec: Function to compute sensitivity and specificity for a binary...
In bhklab/survcomp: Performance Assessment and Comparison for Survival Analysis

Description Usage Arguments Details Value Author(s) References See Also Examples

The function is a wrapper for the survivalROC.C function in order to compute sensitivity and specificity for a binary classification of survival data.

1 2	td.sens.spec(cl, surv.time, surv.event, time, span = 0, sampling = FALSE, na.rm = FALSE, ...)

`cl`	vector of binary classes.
`surv.time`	vector of times to event occurrence.
`surv.event`	vector of event occurrence indicators.
`time`	time point for sensitivity and specificity estimations.
`span`	Span for the NNE. Default value is 0.
`sampling`	jackknife procedure to estimate the standard error of sensitivity and specificity estimations.
`na.rm`	`TRUE` if the missing values should be removed from the data, `FALSE` otherwise.
`...`	additional arguments to be passed to the `survivalROC` function.

Only NNE method is used to estimate sensitivity and specificity (see survivalROC.C). The standard error for sensitivity and specificity is estimated through jackknife procedure (see jackknife).

`sens`	sensitivity estimate
`sens.se`	standard error for sensitivity estimate
`spec`	specificity estimate
`spec.se`	standard error for specificity estimate

Benjamin Haibe-Kains

Heagerty, P. J. and Lumley, T. L. and Pepe, M. S. (2000) "Time-Dependent ROC Curves for Censored Survival Data and a Diagnostic Marker", Biometrics, 56, pages 337–344.

Efron, B. and Tibshirani, R. (1986). "The Bootstrap Method for standard errors, confidence intervals, and other measures of statistical accuracy", Statistical Science, 1 (1), pages 1–35.

survivalROC

set.seed(12345)
gender <- sample(c(0,1), 100, replace=TRUE)
stime <- rexp(100)
cens <- runif(100,.5,2)
sevent <- as.numeric(stime <= cens)
stime <- pmin(stime, cens)
mysenspec <- td.sens.spec(cl=gender, surv.time=stime, surv.event=sevent,
  time=1, span=0, na.rm=FALSE)