Package {ROCsurvcomp}

ROC-Based Methods for Comparing Survival Distributions with Right, Left, and Doubly Censored Data

Description

Performs nonparametric and semiparametric comparisons of two survival distributions under right, left, or double censoring using ROC-based metrics, including ROC curve length, overlap coefficient (OVL), and a joint ROC length–OVL test.

Usage

surv.comp(
  time,
  status,
  group,
  censor_type,
  method,
  n_perm,
  progress = TRUE,
  plot = FALSE
)

Arguments

Details

This function implements permutation-based two-sided hypothesis tests for comparing two survival distributions without relying on proportional hazards assumptions. The ROC length measures global separation between survival curves, while the overlap coefficient (OVL) quantifies distributional similarity. Density estimation is performed using nonparametric kernel methods, where the cumulative distribution function (CDF) is estimated using the Kaplan–Meier estimator under right censoring and the Turnbull estimator under left and double censoring.

Value

A list containing:

• message: A character string describing the testing procedure.

• result: A data frame with rows corresponding to the selected methods (ROC Length, OVL, and/or Joint ROC Length-OVL) and columns:

  • estimate: Estimated values of ROC length and/or OVL

  • p_value: Permutation-based two-sided p-values.

• plot: A ggplot2 object showing the convex hull visualization of the permutation distribution for the joint ROC length-OVL test. This is returned only when method = "joint_method" and plot = TRUE; otherwise, it is NULL.

References

Pepe MS (2003). The Statistical Evaluation of Medical Tests for Classification and Prediction. Oxford University Press.

Bantis LE, Tsimikas JV, Chambers G, Capello M, Hanash S, Feng Z (2021). The length of the ROC curve and the two cutoff Youden index within a robust framework for discovery, evaluation, and cutoff estimation in biomarker studies involving improper ROC curves. Statistics in Medicine, 40(7), 1767–1789.

Franco-Pereira AM, Nakas CT, Reiser B, Pardo MC (2021). Inference on the overlap coefficient: The binormal approach and alternatives. Statistical Methods in Medical Research, 30(12), 2672–2684.

Examples

# Example usage
library(ROCsurvcomp)
library(PWEXP)

# Generating right-censored data with crossing survivals
set.seed(126)
n_trt <- 50
break_trt <- c(2, 4)
rate_trt <- c(log(2)/3, log(2)/7, log(2)/20)
rate.censor_trt <- c(log(2)/55, log(2)/62, log(2)/68)
event_trt <- PWEXP::rpwexp(n_trt, rate = rate_trt, breakpoint = break_trt)
censor_trt <- PWEXP::rpwexp(n_trt, rate = rate.censor_trt, breakpoint = break_trt)
n_ctrl <- 50
rate_ctrl <- log(2)/10
rate.censor_ctrl <- log(2)/58
event_ctrl <- rexp(n_ctrl, rate = rate_ctrl)
censor_ctrl <- rexp(n_ctrl, rate = rate.censor_ctrl)

# Observed time and censoring status (0 = event, 1 = right-censored)
time_trt <- pmin(event_trt, censor_trt)
status_trt <- ifelse(event_trt <= censor_trt, 0, 1)
time_ctrl <- pmin(event_ctrl, censor_ctrl)
status_ctrl <- ifelse(event_ctrl <= censor_ctrl, 0, 1)
time <- c(time_trt, time_ctrl)
status <- c(status_trt, status_ctrl)
group <- c(rep(1, n_trt), rep(2, n_ctrl))

# Run surv.comp()
# Note: n_perm = 10 is used here only for illustration purposes.
# Highly recommended n_perm to be set at 50,000 or more.
surv.comp(time = time, status = status, group = group, censor_type = "right",
          method = "roc_length", n_perm = 10, progress = TRUE, plot = FALSE)