R: Simulation study for bivariate correlated frailty models.

simstdybcf {bcfrailph}

R Documentation

Simulation study for bivariate correlated frailty models.

Description

Simulation study for bivariate correlated gamma and lognormal frailty models with and without covariates.

Usage

simstdybcf(
  Rep,
  mfit = NULL,
  psize,
  cenr = c(0),
  beta = c(0.5),
  frailty,
  frailpar = c(0.5, 0.25),
  bhaz = c("weibull"),
  bhazpar = list(shape = c(0.5), scale = c(0.01)),
  covartype = c("B"),
  covarpar = list(fargs = c(1), sargs = c(0.5)),
  inpcovar = NULL,
  inpcen = NULL,
  comncovar = NULL
)

Arguments

`Rep`	number of replications.
`mfit`	A type of frailty model to be fit in addition to `bcfrailph`. mfit can be c("cox","shrg") where `cox` is for univariate or bivariate shared lognormal and gamma model fit using `coxph` and `shrg` is for univariate or bivariate shared gamma model fit using `shrgamsp`.
`psize`	pair size.
`cenr`	censored rate. The default is zero..
`beta`	Covariate coefficient.
`frailty`	A type of frailty distribution to be used. Either gamma or lognormal.
`frailpar`	vector of frailty parameters, variance and correlation respectively. The default is c(0.5,0.25) meaning variance 0.5 and correlation 0.25.
`bhaz`	A type of baseline hazard distribution to be used. it can be weibull, gompertz or exponential.
`bhazpar`	is a `list` containing `scale` and`shape` of the specified baseline hazard distribution.
`covartype`	specified the distribution from which covariate(s) are goining to be sampled. covartype can be c("B","N","U")denoting binomial, normal or uniform, respectively. For example, `covartype=c("B","B")` to generate two covariates both from a binomial distribution.
`covarpar`	is a `list` containing parmeters of the specified covariate distribution with first and second arguments denoted by `fargs` and `sargs`, respectively. For example, if `covartype=c("B","U")` and `covarpar=list(fargs=c(1,0.3),sargs=c(0.5,1.3))`, generates two independent covariates from a binomial distribution (with parameters size=1 and probs=0.5) and from uniform distributions (with parameters min=0.3 and max=1.3).
`inpcovar`	is a `list` i.e,list(covar1=x1,covar2=x2) to input covariates with both x1 and x2 is in matrix form.
`inpcen`	is a `list` containing `cent1` and `cent2` denoting censoring time for the first and the second subjects in pairs respectively.
`comncovar`	if common covariates are needed.

Value

An object of class simstdybcf that contain the following:

Result a summary result containing true parameter, mean of estimates, mean of the standard errors of the estimates, standard deviation of estimates, and 95% CI coverage probability.
estimates a matrix containing estimates of parameters at each replications.
estimateSE a matrix containing standard error of estimates at each replications.
coverage a matrix containing an indicator whether the true parameter lies within a 95% CI at each replications or not.
TMAT a matrix containing the generated artificial unique event times at each replications for gamma model.
h0MAT a matrix containing the estimated baseline hazards at each replications for gamma model.
h0SEMAT a matrix containing SE of the estimated baseline hazards at each replications for gamma model.

Examples

set.seed(2)
sim<-simstdybcf(Rep=5,psize=100, cenr= c(0.2),beta=c(1,-0.7,0.5),
frailty=c("lognormal"),frailpar=c(0.5,-0.25),bhaz=c("exponential"),
bhazpar=list(scale = c(0.1)),covartype= c("N","N","B"),
covarpar=list(fargs=c(0,0,1),sargs=c(1,1,0.5)),comncovar=2)
Res<-sim$Result
Res


# In addition to bcfrailph fit, if coxph with univariate lognormal frailty model is desired to run,

sim<-simstdybcf(Rep=5,mfit="cox",psize=100, cenr= c(0.2),beta=c(1,-0.7,0.5),
frailty=c("lognormal"),frailpar=c(0.5,-0.25),bhaz=c("exponential"),
bhazpar=list(scale = c(0.1)),covartype= c("N","N","B"),
covarpar=list(fargs=c(0,0,1),sargs=c(1,1,0.5)),comncovar=2)
Res<-sim$Result # bcfrailph fit result
Res
Resc<-sim$Resultc # coxph with univariate lognormal frailty model fit result
Resc