Package 'crrcbcv'

Clustered competing risks simulated data

Description

sample of 20 clusters with an average cluster size of 20

Usage

data(cls)

Format

A data frame containing 20 clusters with an average cluster size of 20 and the following five variables. Simulation is detailed in the paper Finite-sample adjustments in variance estimators for clustered competing risks regression. Chen, Li. 2022. Under Review. Statistics in Medicine.

I

id of clusters

X_1

a cluster-level covariate generated from the standard normal distribution

X_2

an individual-level covariate generated from the standard normal distribution

eps

event type. 0=censored, 1, 2

T_obs

observed event time

Author(s)

Xinyuan Chen, ⁠<[email protected]>⁠

Fan Li, ⁠<[email protected]>⁠

References

Chen X, Li F. (2022). Finite-sample adjustments in variance estimators for clustered competing risks regression. Statistics in Medicine. 00(Under Review): 1-24.

Examples

data(cls)

---

Bias-Corrected Variance for Competing Risks Regression with Clustered Data

Description

Small-sample bias-corrected variance for regression modeling using proportional subdistribution hazards with clustered right censored data. (Zhou et al., 2012) Failure times within the same cluster are dependent.

Four types of bias correction are included: the MD-type correction by Mancl and DeRouen (2001), the KC-type correction by Kauermann and Carroll (2001), the FG-type correction by Fay and Graubard (2001), and the MBN-type correction by Morel, Bokossa, and Neerchal (2003).

Usage

crrcbcv(
  beta,
  ftime,
  fstatus,
  cov1,
  cov2,
  tf,
  cluster,
  failcode = 1,
  cencode = 0,
  subset,
  na.action = na.omit,
  var.type = "MD"
)

Arguments

beta	the estimated regression coefficients from crrc
ftime	vector of failure/censoring times
fstatus	vector with a unique code for each failure type and a separate code for censored observations
cov1	matrix (nobs x ncovs) of fixed covariates (either cov1, cov2, or both are required)
cov2	matrix of covariates that will be multiplied by functions of time; if used, often these covariates would also appear in cov1 to give a prop hazards effect plus a time interaction
tf	functions of time. A function that takes a vector of times as an argument and returns a matrix whose jth column is the value of the time function corresponding to the jth column of cov2 evaluated at the input time vector. At time tk, the model includes the term cov2[,j]*tf(tk)[,j] as a covariate
cluster	clustering indicator
failcode	code of fstatus that denotes the failure type of interest
cencode	code of fstatus that denotes censored observations
subset	a logical vector specifying a subset of cases to include in the analysis
na.action	a function specifying the action to take for any cases missing any of ftime, fstatus, cov1, cov2, cengroup, or subset
var.type	a string or a vector of strings with value(s) selected from {"MD", "KC", "FG", "MBN"}

Value

Returns a list of class crr, with components corresponding to var.type

⁠$MD⁠

the MD-type bias-corrected variance covariance matrix for beta

⁠$KC⁠

the KC-type bias-corrected variance covariance matrix for beta

⁠$FG⁠

the FG-type bias-corrected variance covariance matrix for beta

⁠$MBN⁠

the MBN-type bias-corrected variance covariance matrix for beta

Author(s)

Xinyuan Chen, ⁠<[email protected]>⁠

Fan Li, ⁠<[email protected]>⁠

References

Chen X, Li F. (2022). Finite-sample adjustments in variance estimators for clustered competing risks regression. Statistics in Medicine. 00(Under Review): 1-24.

Zhou B, Fine J, Latouche A, Labopin M. (2012). Competing risks regression for clustered Data. Biostatistics. 13(3): 371-383.

See Also

crrSC

Examples

library(crrcbcv)
data(cls)
mod.est = crrc(ftime=cls$T_obs, fstatus=cls$eps, cov1=cls[,c('X_1','X_2')], cluster=cls$I)
crrcbcv(beta=mod.est$coef, ftime=cls$T_obs, fstatus=cls$eps, cov1=cls[,c('X_1','X_2')],
cluster=cls$I, var.type=c('MD','KC','FG','MBN'))

---