plotPredictRisk {riskRegression}

Plotting predicted risks curves.

Description

Time-dependent event risk predictions.

Usage

plotPredictRisk(
  x,
  newdata,
  times,
  cause = 1,
  xlim,
  ylim,
  xlab,
  ylab,
  axes = TRUE,
  col,
  density,
  lty,
  lwd,
  add = FALSE,
  legend = TRUE,
  percent = FALSE,
  ...
)

Arguments

x

Object specifying an event risk prediction model.

newdata

A data frame with the same variable names as those that were used to fit the model x.

times

Vector of times at which to return the estimated probabilities.

cause

Show predicted risk of events of this cause

xlim

Plotting range on the x-axis.

ylim

Plotting range on the y-axis.

xlab

Label given to the x-axis.

ylab

Label given to the y-axis.

axes

Logical. If FALSE no axes are drawn.

col

Vector of colors given to the survival curve.

density

Densitiy of the color – useful for showing many (overlapping) curves.

lty

Vector of lty's given to the survival curve.

lwd

Vector of lwd's given to the survival curve.

add

Logical. If TRUE only lines are added to an existing device

legend

Logical. If TRUE a legend is plotted by calling the function legend. Optional arguments of the function legend can be given in the form legend.x=val where x is the name of the argument and val the desired value. See also Details.

percent

Logical. If TRUE the y-axis is labeled in percent.

...

Parameters that are filtered by SmartControl and then passed to the functions: plot, axis, legend.

Details

Arguments for the invoked functions legend and axis can be specified as legend.lty=2. The specification is not case sensitive, thus Legend.lty=2 or LEGEND.lty=2 will have the same effect. The function axis is called twice, and arguments of the form axis1.labels, axis1.at are used for the time axis whereas axis2.pos, axis1.labels, etc., are used for the y-axis.

These arguments are processed via ...{} of plotPredictRisk and inside by using the function SmartControl.

Value

The (invisible) object.

Author(s)

Ulla B. Mogensen and Thomas A. Gerds [e-mail]

References

Ulla B. Mogensen, Hemant Ishwaran, Thomas A. Gerds (2012). Evaluating Random Forests for Survival Analysis Using Prediction Error Curves. Journal of Statistical Software, 50(11), 1-23. URL http://www.jstatsoft.org/v50/i11/.

See Also

plotRisk

Examples

library(survival)
# generate survival data
# no effect
set.seed(8)
d <- sampleData(80,outcome="survival",formula = ~f(X6, 0) + f(X7, 0))
d[,table(event)]
f <- coxph(Surv(time,event)~X6+X7,data=d,x=1)
plotPredictRisk(f)

# large effect
set.seed(8)
d <- sampleData(80,outcome="survival",formula = ~f(X6, 0.1) + f(X7, -0.1))
d[,table(event)]
f <- coxph(Surv(time,event)~X6+X7,data=d,x=1)
plotPredictRisk(f)

# generate competing risk data
# small effect
set.seed(8)
d <- sampleData(40,formula = ~f(X6, 0.01) + f(X7, -0.01))
d[,table(event)]
f <- CSC(Hist(time,event)~X5+X6,data=d)
plotPredictRisk(f)

# large effect
set.seed(8)
d <- sampleData(40,formula = ~f(X6, 0.1) + f(X7, -0.1))
d[,table(event)]
f <- CSC(Hist(time,event)~X5+X6,data=d)
plotPredictRisk(f)