TwoSSP: Create a two-sample survival probability curve for data from...

In SandraCastroPearson/2SPcurves: A Package for the Analysis of Time to Event Outcomes Using Two-Sample Probability Curves

Create a two-sample survival probability curve for data from randomized controlled trials.

Description

This function creates a two-samle survival probability curve for data from randomized controlled trials and has options to estimate the AUC, diagnose the proportional hazard assumptions and more.

Usage

TwoSSP(
  time,
  event,
  group,
  area = TRUE,
  silent = FALSE,
  CI = FALSE,
  level = 0.95,
  B = 1000,
  checkPH = FALSE,
  compare = FALSE,
  abtwc = FALSE,
  xlab = NULL,
  ylab = NULL,
  main = NULL,
  cex.axis = 1.5,
  cex.lab = 1.5,
  legend.inset = 0.02,
  legend.cex = 1.5,
  lty = c(2, 1, 3),
  lwd = 1.5
)

Arguments

time	Time to event or censoring.
event	An indicator vector with values of 1 for individuals who had the event occur or 0 if the participant was censored.
group	An indicator vector with values of 1 if the the participant was in the treatment arm and 0 otherwise.
area	Logical argument to indicate if user wants an estimate for area under the curve (default is TRUE).
silent	Logical argument, FALSE indicates the user wants plots and TRUE indicates no plots only AUC calculations (default is FALSE).
CI	Logical argument indicating if user wants bootstrap errors and confidence intervals to be calculated for the curve and AUC. Default is FALSE.
level	Numerical argument indicating condifence level for the confidence interval. Default is 0.95. It's ignored if CI=FALSE.
B	Number of bootstrap samples to use for confidence interval and error calculations. Default is 1000. It's ignored if CI=FALSE.
checkPH	Logical argument to indicate if user wants to compare the nonparametric curve with the curve based on the proportional hazards model (default is FALSE).
compare	Logical argument to indicate if user wants want to compare the nonparametric curve with curves based on a proportional hazards model, proportional odds model, and various AFT models (default is FALSE).
abtwc	Logical argument to indicate if area between curves is needed as part of model comparisons (checkPHM or compare must be TRUE).
xlab	String argument for the horizontal axis label of the ROC curve.
ylab	String argument for the vertical axis label of the ROC curve.
main	String argument for the title of the ROC curve.
cex.axis	Optional graphical parameter for magnification of axis annotation. See par for more details.
cex.lab	Optional graphical parameter for magnification of x and y labels. See par for more details.
legend.inset	Optional graphical parameter controling the inset of the legend.
legend.cex	Optional graphical parameter for magnification of the legend's text.
lty	Optional graphical parameter to set the type of line to use. Can be a number or a vector. See par for more details.
lwd	Optional graphical parameter for line width relative to the default. See par for more details.

Value

A plot of the ROC curve (if silent=FALSE) and an ROCsurv object containing:

• A survfit object containing the survival curve for the treatment group.

• A survfit object containing the survival curve for the control group.

• The area under the curve (AUC).

• A matrix representation of the two-sample survival probability curve R_u.

SandraCastroPearson/2SPcurves documentation built on June 15, 2022, 3:42 a.m.