Copula.surv (version 3.0)

simu.BB1reg: Simulating data from the BB1 copula regression model

Description

n pairs of (U,V) are generated from the BB1 copula. n paris of (X,Y) are generated from the corresponding bivariate survival model with the Weibull marginal distributions. The default parameters (scale1=scale2=shape1=shape2=1) give the unit exponential distributions.

Usage

simu.BB1reg(n,alpha,delta=0,scale1=1,scale2=1,shape1=1,shape2=1,
 beta1=0,beta2=0,beta12=0,Z.dist=runif,...)

Value

U

uniformly distributed on (0,1)

V

uniformly distributed on (0,1)

X

Weibull distributed (scale1, shape1)

Y

Weibull distributed (scale2, shape2)

Z

Covariates

Arguments

n

sample size

alpha

association (copula) parameter

delta

BB1 copula's departure parameter from the Clayton (0 is the default)

scale1

scale parameter for X

scale2

scale parameter for Y

shape1

shape parameter for X

shape2

shape parameter for Y

beta1

regression coefficient for X

beta2

regression coefficient for Y

beta12

regression coefficient for copula

Z.dist

distribution for covariates

...

parameters for Z.dist

Author

Takeshi Emura

Details

See Section 2.6 of Emura et al.(2019) for copulas and bivariate survival times.

References

Emura T, Lin CW, Wang W (2010) A goodness-of-fit test for Archimedean copula models in the presence of right censoring, Compt Stat Data Anal 54: 3033-43

Emura T, Matsui S, Rondeau V (2019), Survival Analysis with Correlated Endpoints, Joint Frailty-Copula Models, JSS Research Series in Statistics, Springer

Examples

n=10
simu.BB1reg(n=n,alpha=1,delta=2,scale1=1,scale2=2,shape1=0.5,beta1=1,beta2=-1,beta12=2,shape2=2)