cif2.int {surv2sample} | R Documentation |
Compares cumulative incidence functions (CIF) for one failure cause in two samples of censored competing risks data using the test based on the integrated difference of CIFs.
cif2.int(x, group, cause = 1, tau, nsim = 0)
x |
a "Survcomp" object, as returned by the
Survcomp function. |
group |
a vector indicating to which group each observation belongs. May contain values 1 and 2 only. |
cause |
For which cause of failure should the CIFs be compared? |
tau |
the upper limit of the integral in the test statistic. If missing, defaults to the maximum of times. |
nsim |
the number of simulations used to approximate the distribution of the test statistic. If 0, no simulations are carried out and the asymptotic normal approximation is used. |
The test compares cumulative incidence functions F_1(t,k), F_2(t,k) for a particular failure cause k.
The method is based on the statistic proposed by Pepe (1991) which is the integral of F_2(t,k)-F_1(t,k) from 0 to tau. The martingale-based simulation technique and the variance estimator are described in Bajorunaite and Klein (2007).
A list of class "cif2.int"
with components:
stat |
the test statistic. |
pval.asympt |
the p-value based on the asymptotic normality. |
pval.sim |
the p-value based on simulations (if nsim >0). |
Further components are cause
, tau
, nsim
, the same
as on input.
David Kraus (http://www.davidkraus.net/)
Bajorunaite, R. and Klein, J. P. (2007) Two-sample tests of the equality of two cumulative incidence functions. Comput. Statist. Data Anal. 51, 4269–4281.
Pepe, M. S. (1991) Inference for events with dependent risks in multiple endpoint studies. J. Amer. Statist. Assoc. 86, 770–778.
cif
and plot.cif
for estimation and
plotting of CIFs
cif2.ks
, cif2.logrank
and
cif2.neyman
for other two-sample tests
## bone marrow transplant data data(bmt1) ## compare CIFs for cause 1 (relapse) cif2.int(Survcomp(bmt1$time, bmt1$event), bmt1$donor, cause = 1) ## compare CIFs for cause 2 (death in remission) cif2.int(Survcomp(bmt1$time, bmt1$event), bmt1$donor, cause = 2)