comp.graph: Plot a 'cox.ridge' or 'cox.dynamic.ridge' object.
In CoxRidge: Cox Models with Dynamic Ridge Penalties

Description Usage Arguments Details References See Also Examples

Plots time varying effects of covariates.

1 2	comp.graph(obj, alpha = 0.05, xlab = "time", ylab = "X effect", all.terms = TRUE, variable)

`obj`	A `cox.ridge` or `cox.dynamic.ridge` object.
`alpha`	The alpha level used for confidence bands.
`xlab`	a title for the x axis
`ylab`	a title for the y axis
`all.terms`	When TRUE all time-varying effects variables are plotted.
`variable`	when all.terms=FALSE you need to specify which variable to be plotted. Use numbers 1,2,3... for first, second, third etc.

Confidence bands are computed using the delta method.

Perperoglou A, le Cessie S, van Houwelingen HC (2006). Reduced-rank hazard regression for modelling non-proportional hazards. Statistics in Medicine: 25, 2831-2845

plot

data(ova)
attach(ova)
X <- cbind(karn,diam,figo)
X <- apply(X,2,function(x){(x-mean(x))/sqrt(var(x))})
Ft <- cbind(rep(1,nrow(X)),bs(time))
fit <- Dynamic.Ridge(time,death,X,Ft=Ft,fun="simple")
comp.graph(fit,all.terms=FALSE,variable=1)
par(mfrow=c(3,1))
comp.graph(fit)