timereg (version 1.3-6)

plot.cum.residuals: Plots cumulative residuals

Description

This function plots the output from the cumulative residuals function "cum.residuals". The cumulative residuals are compared with the performance of similar processes under the model.

Usage

## S3 method for class 'cum.residuals':
plot(x,pointwise.ci=1,hw.ci=0,sim.ci=0,
robust=1, specific.comps=FALSE,level=0.05,start.time=0,stop.time=0,
add.to.plot=FALSE,mains=TRUE,xlab="Time",
ylab ="Cumulative Residuals",ylim=NULL,score=0,conf.band=FALSE,...)

Arguments

x

the output from the "cum.residuals" function.

pointwise.ci

if >1 pointwise confidence intervals are plotted with lty=pointwise.ci

hw.ci

if >1 Hall-Wellner confidence bands are plotted with lty=hw.ci. Only 95% bands can be constructed.

sim.ci

if >1 simulation based confidence bands are plotted with lty=sim.ci. These confidence bands are robust to non-martingale behaviour.

robust

if "1" robust standard errors are used to estimate standard error of estimate, otherwise martingale based estimate are used.

specific.comps

all components of the model is plotted by default, but a list of components may be specified, for example first and third "c(1,3)".

level

gives the significance level. Default is 0.05.

start.time

start of observation period where estimates are plotted. Default is 0.

stop.time

end of period where estimates are plotted. Estimates thus plotted from [start.time, max.time].

add.to.plot

to add to an already existing plot. Default is "FALSE".

mains

add names of covariates as titles to plots.

xlab

label for x-axis. Default is "Time".

ylab

label for y-axis. Default is "Cumulative Residuals".

ylim

limits for y-axis.

score

if '0' plots related to modelmatrix are specified, thus resulting in grouped residuals, if '1' plots for modelmatrix but with random realizations under model, if '2' plots residuals versus continuous covariates of model with random realizations unde

conf.band

makes simulation based confidence bands for the test processes under the 0 based on variance of these processes limits for y-axis. These will give additional information of whether the observed cumulative residuals are extreme or not when based on a var

...

unused arguments - for S3 compatibility

References

Martinussen and Scheike, Dynamic Regression Models for Survival Data, Springer (2006).

Examples

library(survival)
data(sTRACE)
# Fits Aalen model and returns residuals
out<-aalen(Surv(time,status==9)~age+sex+diabetes+chf+vf,
sTRACE,max.time=7,n.sim=0,residuals=1)

# constructs and simulates cumulative residuals versus age groups
out.mg<-cum.residuals(out,sTRACE,model.matrix(~-1+factor(cut(age,4)),sTRACE),n.sim=100)

par(mfrow=c(1,4))
# cumulative residuals with pointwise confidence intervals 
plot(out.mg);
# cumulative residuals versus processes under model
plot(out.mg,score=1);

# cumulative residuals against covariates Lin, Wei, Ying style
out.mg<-cum.residuals(out,sTRACE,cum.resid=1,n.sim=100)
par(mfrow=c(2,4))
plot(out.mg,score=2)