riskRegression (version 1.1.7)

CSC: Cause-specific Cox proportional hazard regression

Description

Interface for fitting cause-specific Cox proportional hazard regression models in competing risk.

Usage

CSC(formula, data, cause, survtype = "hazard", fitter = "coxph", ...)

Arguments

formula

A list of formulae, one for each cause, each specifying a cause-specific Cox regression model.

data

A data in which to fit the models.

cause

The cause of interest. Defaults to the first cause.

survtype

Either "hazard" (the default) or "survival". If "hazard" fit cause-specific Cox regression models for all causes. If "survival" fit one cause-specific Cox regression model for the cause of interest and

fitter

Routine to fit the Cox regression models. If coxph use survival::coxph else use rms::cph. The latter is much faster when it comes to prediction.

...

Arguments given to coxph.

Value

• models
  a list with the fitted (cause-specific) Cox regression objects
• response
  the event history response
• eventTimes
  the sorted (unique) event times
• survtype
  the value of survtype
• theCause
  the cause of interest. see cause
• causes
  the other causes

See Also

coxph

Examples

library(riskRegression)
library(prodlim)
library(pec)
library(survival)
data(Melanoma)
## fit two cause-specific Cox models
## different formula for the two causes
fit1 <- CSC(list(Hist(time,status)~sex,Hist(time,status)~invasion+epicel+age),
            data=Melanoma)
print(fit1)
fit1a <- CSC(list(Hist(time,status)~sex+age,Hist(time,status)~invasion+epicel+log(thick)),
             data=Melanoma,
             survtype="surv")
print(fit1a)

## same formula for both causes
fit2 <- CSC(Hist(time,status)~invasion+epicel+age,
            data=Melanoma)
print(fit2)

## combine a cause-specific Cox regression model for cause 2
## and a Cox regression model for the event-free survival:
## different formula for cause 2 and event-free survival
fit3 <- CSC(list(Hist(time,status)~sex+invasion+epicel+age,
                 Hist(time,status)~invasion+epicel+age),
            survtype="surv",
            data=Melanoma)
print(fit3)

## same formula for both causes
fit4 <- CSC(Hist(time,status)~invasion+epicel+age,
            data=Melanoma,
            survtype="surv")
print(fit4)

## strata
fit5 <- CSC(Hist(time,status)~invasion+epicel+age+strata(sex),
            data=Melanoma,
            survtype="surv")
print(fit5)

## sanity check

cox1 <- coxph(Surv(time,status==1)~invasion+epicel+age+strata(sex),data=Melanoma)
cox2 <- coxph(Surv(time,status!=0)~invasion+epicel+age+strata(sex),data=Melanoma)
all.equal(cox1,fit5$models[[1]])
all.equal(cox2,fit5$models[[2]])

## predictions
##
## survtype = "hazard": predictions for both causes can be extracted
## from the same fit
library(pec)
fit2 <- CSC(Hist(time,status)~invasion+epicel+age, data=Melanoma)
pec:::predictEventProb(fit2,cause=1,newdata=Melanoma[c(17,99,108),],times=c(100,1000))
pec:::predictEventProb(fit2,cause=2,newdata=Melanoma[c(17,99,108),],times=c(100,1000))

## survtype = "surv" we need to change the cause of interest

fit5.2 <- CSC(Hist(time,status)~invasion+epicel+age+strata(sex),
            data=Melanoma,
            survtype="surv",cause=2)
## now this does not work
try(pec:::predictEventProb(fit5.2,cause=1,newdata=Melanoma,times=4))

## but this does
try(pec:::predictEventProb(fit5.2,cause=2,newdata=Melanoma,times=100))