stdReg (version 3.4.1)

plot.stdCoxph: Plots Cox regression standardization fit

Description

This is a plot method for class "stdCoxph".

Usage

# S3 method for stdCoxph
plot(x, plot.CI = TRUE, CI.type = "plain", CI.level = 0.95,
  transform = NULL, contrast = NULL, reference = NULL, legendpos="bottomleft", ...)

Arguments

x

an object of class "stdCoxph".

plot.CI

logical, indicating whether confidence intervals should be added to the plot.

CI.type

string, indicating the type of confidence intervals. Either "plain", which gives untransformed intervals, or "log", which gives log-transformed intervals.

CI.level

desired coverage probability of confidence intervals, on decimal form.

transform

a string. If set to "log", "logit", or "odds", the standardized survival function \(\theta(t,x)\) is transformed into \(\psi(t,x)=log\{\theta(t,x)\}\), \(\psi(t,x)=log[\theta(t,x)/\{1-\theta(t,x)\}]\), or \(\psi(t,x)=\theta(t,x)/\{1-\theta(t,x)\}\), respectively. If left unspecified, \(\psi(t,x)=\theta(t,x)\).

contrast

a string. If set to "difference" or "ratio", then \(\psi(t,x)-\psi(t,x_0)\) or \(\psi(t,x) / \psi(t,x_0)\) are constructed, where \(x_0\) is a reference level specified by the reference argument.

reference

must be specified if contrast is specified.

legendpos

position of the legend; see help for legend.

…

further arguments passed on to plot.default.

See Also

stdCoxph

Examples

# NOT RUN {
##See documentation for stdCoxph

# }