fcov.crr: Checking the functional form assumption for Fine & Gray model

In goftte: Goodness-of-Fit for Time-to-Event Data

Description

Diagnostics for the linear functional form of specific covariate(s) of the Fine & Gray model. Similarly to Li (2015), we extend the Lin's approximation method to take into account competing events. We also provide an adaptation of Liu's approximation method (2008) for Fine & Gray models. P-values are derived for supremum KS test statistics.

Usage

## S3 method for class 'crr'
fcov(model, fstatus, ftime, cov1, cencode=0, failcode=1,  type.test=c("Lin"), R=1000,  
plots=min(R,50),  seed=NULL, variable=NULL,...)
       

Arguments

model	Model object (crr).
fstatus	Vector corresponding to the failures of the n patients.
ftime	Vector corresponding to the failure times.
cov1	Matrix whose columns consist in the components of the p covariates.
cencode	Censoring code.
failcode	Interest event code. All the failures differing from cencode and faildcode are considered as competing events.
type.test	Type of approximation. Values are "Lin" or "Liu". Default is "Lin".
R	Generation number used for Monte-Carlo simulations. This is also an output argument.
plots	Realizations number of Monte-Carlo simulations to save for use in the plot-routine.
seed	Random seed.
variable	Vector corresponding to the labels of each covariate. This is also an output argument.
...	additional arguments.

Value

Returns an object of class 'scproc'. The main items of this object are :

obs	l x p matrix of unique covariates values. l is the maximum number of unique observation between the p covariates.
W	The process U(\widehat{β},z) adapted to Fine & Gray model.
What	The simulated limiting processes for the R-plots first Monte-Carlo realizations.
sdw	Standard error over covariates values of What.
cvalues	R x p matrix whose components are the supremum of the standardized What process for each Monte-Carlo realization. The quantiles of this output argument are used to calculate the prediction bands in the plot-routine.
KS	Vector of the p rejection probabilities using KS type statistic.

Author(s)

Patrick Sfumato and Jean-Marie Boher.

References

Li J, Scheike TH and Zhang MJ (2015). Checking Fine & Gray subditribution hazards model with cumulative sums of residuals. Lifetime Data Analysis, 21(2), 197-217.

Lin DY, Wei JL and Ying Z (1993).Checking the Cox model with cumulative sums of martingale-based residuals. Biometrika, 80(3), 557-572.

Liu M, Lu W and Shao (2008). A Monte Carlo approach for change-point detection in the Cox proportional hazards model. Statistics in Medecine, 27(19), 3894-3909.

Examples

require(cmprsk)

#Simulating survival data with competing events
set.seed(10)
ftime <- rexp(200)
fstatus <- sample(0:2,200,replace=TRUE)
cov <- matrix(runif(200),nrow=200)

# Fine & Gray regression
fit.crr <- crr(ftime,fstatus,cov)

#Checking the covariates functional form assumption
fcov(model=fit.crr, ftime=ftime,fstatus=fstatus,cov1=cov)
       

goftte documentation built on May 2, 2019, 5:12 a.m.