Computes concordance and probandwise concordance for dependence models for competing risks models of the type cor.cif, rr.cif or or.cif for the given cumulative incidences and the different dependence measures in the object.

1 2 3 |

`object` |
object from cor.cif rr.cif or or.cif for dependence between competing risks data for two causes. |

`marg.cif` |
a number that gives the cumulative incidence in one time point for which concordance and probandwise concordance are computed. |

`marg.cif2` |
the cumulative incidence for cause 2 for concordance and probandwise concordance are computed. Default is that it is the same as marg.cif. |

`digits` |
digits in output. |

`...` |
Additional arguments. |

prints summary for dependence model.

`probandwise` |
gives probandwise concordance that is, probability of cause 2 (related to cif2) given that cause 1 (related to cif1) has occured. |

`concordance` |
gives concordance that is, probability of cause 2 (related to cif2) and cause 1 (related to cif1). |

`cif1` |
cumulative incidence for cause1. |

`cif2` |
cumulative incidence for cause1. |

Thomas Scheike

Cross odds ratio Modelling of dependence for Multivariate Competing Risks Data, Scheike and Sun (2012), Biostatistics to appear.

A Semiparametric Random Effects Model for Multivariate Competing Risks Data, Scheike, Zhang, Sun, Jensen (2010), Biometrika.

1 2 3 4 5 6 7 8 9 10 11 12 | ```
data(multcif) # simulated data
multcif$cause[multcif$cause==0] <- 2
times=seq(0.05,3,by=0.1) # to speed up computations use only these time-points
add<-comp.risk(Event(time,cause)~const(X)+cluster(id),data=multcif,
n.sim=0,times=times,cause=1)
###
out1<-cor.cif(add,data=multcif,cause1=1,cause2=1,theta=log(2+1))
summary(out1)
pad <- predict(add,X=1,Z=0,se=0,uniform=0)$P1
summary(out1,marg.cif=pad)
``` |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.