plot.cpsurv {CPsurv} | R Documentation |
Plot method for objects of class cpsurv
Description
Plot method for objects of class 'cpsurv' inheriting from a call to
cpsurv
.
Usage
## S3 method for class 'cpsurv'
plot(x, type = "all", ci = TRUE, ci.type = c("perc",
"norm"), const.haz = TRUE, regline = TRUE, legend = TRUE, xlim = NULL,
ylim = NULL, main = NULL, xlab = NULL, ylab = NULL, min.time,
max.time, n.est.grid = 101, ask = TRUE, ...)
Arguments
x |
An object of class 'cpsurv' (estimated with |
type |
A vector of character strings to select the plots for printing. The value should be any subset of the values c("pvals", "events", "hazard") or simply "all", where all possible plots are shown. |
ci |
Logical; if |
ci.type |
Character representing the type of confidence interval to plot (if existing); "perc" for percentile interval and "norm" for CI with normal approximation (default is "perc"). |
const.haz |
Logical; if |
regline |
Logical; if |
legend |
Logical; if |
xlim |
Vector with x limits (timeline) for each plot if supplied; default is c(0, x$cpmax). |
ylim |
Vector with y limits for plots of type "events" and "hazard". For changing ylim for only one of them, plot them separately by use of argument 'type'. |
main |
Main title for each plot if supplied. |
xlab |
Character vector used as x label for all plots if supplied. |
ylab |
Character vector used as y label for all plots if supplied. |
min.time |
Left bound of time domain used for
|
max.time |
Right bound of time domain used for
|
n.est.grid |
Number of points in the estimation grid, where hazard
estimates are computed (used for |
ask |
If |
... |
Additional arguments passed through to plotting functions. |
Details
The value type = "pvals"
produces a plot with p-values used
to estimate the stump regression model with superimposed least squares
regression line. For type = "events"
a barplot is produced with
frequency of events per unit at risk for each interval (with length
intwd
. For type = "hazard"
the estimated hazard rate (based
on muhaz
) is plotted with optional (normal- or
percentile-) confidence intervals and the estimated constant hazard rate.
See Also
Examples
data(survdata)
cp <- cpsurv(survdata$time, survdata$event, cpmax = 360, intwd = 10)
plot(cp, ask = FALSE)
## Not run:
cp <- cpsurv(survdata$time, survdata$event, cpmax = 360, intwd = 10,
boot.ci = TRUE)
plot(cp, type = "pvals", ask = FALSE)
## End(Not run)