Learn R Programming

eha (version 2.4-5)

check.dist: Graphical goodness-of-fit test

Description

Comparison of the cumulative hazards functions for a semi-parametric and a parametric model.

Usage

check.dist(sp, pp, main = NULL, col = NULL, printLegend = TRUE)

Arguments

sp
An object of type "coxreg", typically output from coxreg
pp
An object of type "phreg", typically output from phreg
main
Header for the plot. Default is distribution and "cumulative hazard function"
col
Line colors. should be NULL (black lines) or of length 2
printLegend
Should a legend be printed? Default is TRUE.

Value

No return value.

Details

For the moment only a graphical comparison. The arguments sp and pp may be swapped.

See Also

coxreg and phreg.

Examples

Run this code
data(mort)
oldpar <- par(mfrow = c(2, 2))
fit.cr <- coxreg(Surv(enter, exit, event) ~ ses, data = mort)
fit.w <- phreg(Surv(enter, exit, event) ~ ses, data = mort)
fit.g <- phreg(Surv(enter, exit, event) ~ ses, data = mort,
dist = "gompertz")
fit.pch <- phreg(Surv(enter, exit, event) ~ ses, data = mort,
dist = "pch", cuts = c(5, 10, 15))
fit.ev <- phreg(Surv(enter, exit, event) ~ ses, data = mort,
dist = "ev")
check.dist(fit.cr, fit.w)
check.dist(fit.cr, fit.g)
check.dist(fit.cr, fit.pch)
check.dist(fit.cr, fit.ev)
par(oldpar)

Run the code above in your browser using DataLab