plot.coxlps: Plot baseline hazard and survival curves from a coxlps object.

Description

Produces a plot of the baseline hazard and/or survival based on a coxlps object.

Usage

# S3 method for coxlps
plot(x, S0 = TRUE, h0 = TRUE, cred.int = 0.95, overlay.km = FALSE,
     plot.cred = FALSE, np = 50, show.legend = TRUE, ...)

Arguments

x: An object of class coxlps.
S0: Logical. Should the estimated baseline survival be plotted?
h0: Logical. Should the estimated baseline hazard be plotted?
cred.int: The level for an approximate pointwise credible interval to be computed for the baseline curves. Default is 0.95.
overlay.km: A logical value indicating whether the Kaplan-Meier estimate should be plotted together with the smooth baseline survival curve. The default is FALSE.
plot.cred: Logical. Should the credible intervals be plotted ? Default is FALSE.
np: The number of points used to plot the smooth baseline functions. Default is 50 and allowed values are between 20 and 200.
show.legend: Logical. Should a legend be displayed?
...: Further arguments to be passed to plot.

Author

Oswaldo Gressani oswaldo_gressani@hotmail.fr.

Details

Plots for the baseline hazard and survival curves are computed on a grid (of length np) between 0 and the 99th percentile of follow-up times. When plot.cred is FALSE, the fit omits to compute the approximate pointwise credible intervals for plotting and hence is less computationally intensive. Vertical ticks on the x-axis correspond to the observed follow-up times.

Examples

Run this code



## Simulate survival data
set.seed(6)
betas <- c(0.35, -0.20, 0.05, 0.80) # Regression coefficients
data <- simsurvdata(a = 1.8, b = 2, n = 200, betas = betas, censperc = 25)
simdat <- data$survdata

# Fit model
fit <- coxlps(Surv(time, delta) ~ x1 + x2 + x3 + x4, data = simdat)
plot(fit, h0 = FALSE, S0 = TRUE, overlay.km = FALSE, show.legend = FALSE)
domt <- seq(0, 5.5, length = 500)
lines(domt, data$S0(domt), type = "l", col = "red")
legend("topright", c("Bayesian LPS", "Target"), col = c("black", "red"),
       lty = c(1, 1), bty = "n", cex = 0.8)