simcoxph function

Simulate survival data and fit models

Generates simulated clustered survival data by repeatedly generating data, using a shared frailty model, and fitting the models. Respective arguments are passed to genfrail and coxph, and the resulting parameter estimates are aggregated and summarized.

This function is similar to simfrail, except models are fitted using the coxph.

simcoxph(reps, genfrail.args, coxph.args, Lambda.times, cores = 0)

Arguments

• reps: number of times to repeat the simulation
• genfrail.args: list of arguments to pass to genfrail
• coxph.args: list of arguments to pass to coxph
• Lambda.times: vector of time points to obtain baseline hazard estimates at
• cores: integer; if > 0, the number of cores to use; if < 0, the number of cores not to use; if 0, use all available cores

Returns

A simcoxph object that is essentially a data.frame of the resulting parameter estimates. Each row is a single run, and columns are as follows.

• seed: the seed used for the run

• runtime: the time it took to fit the model

• N: number of clusters

• mean.K: average cluster size

• cens: empirical censorship

• beta: true regression coefficients

• hat.beta: estimated regression coefficients

• se.beta: standard error of each regression coefficient

• theta: true frailty distribution parameters

• hat.theta: estimated frailty distribution parameters

• se.theta: standard error of each frailty distribution parameter (NA since coxph does not currently provide this.)

• Lambda: true cumulative baseline hazard at each Lambda.times point

• hat.Lambda: estimated cumulative baseline hazard at each Lambda.times point

• se.Lambda: standard error at each Lambda.times point (NA since coxph does not currently provide this)

Author(s)

John. V Monaco, Malka Gorfine, Li Hsu

See Also

coxph, genfrail, simfrail

Examples

## Not run:

sim <- simcoxph(reps=100,
                genfrail.args=alist(
                  N=50, K=2,
                  beta=c(log(2),log(3)), 
                  frailty="gamma", theta=2,
                  Lambda_0 = function(t, tau=4.6, C=0.01) (C*t)^tau), 
                coxph.args=alist(
                  formula=Surv(time, status) ~ Z1 + Z2 + cluster(family), 
                  frailty="gamma"),
                Lambda.times=1:120, cores = 0)

# Summarize the results
summary(sim)

# Plot the residuals
plot(sim, "residuals")
## End(Not run)