simulate_hybrid_cox: Simulate a hybrid-control Cox proportional hazards dataset

In fdb: Frequentist Dynamic Borrowing for Hybrid-Control Survival Trials

Simulate a hybrid-control Cox proportional hazards dataset

Description

Generates a randomized trial augmented with an external control arm, under a Cox proportional hazards model

h(t \mid T,Z,X) = h_0(t)\,\exp(\theta T + \delta Z + \beta^\top X),

where T is the treatment indicator, Z is the external-control indicator, X is a vector of baseline covariates, \theta is the treatment effect, and \delta is the population drift between concurrent and external controls.

Usage

simulate_hybrid_cox(
  nI1 = 150,
  nI0 = 150,
  nE = 300,
  theta0 = 0,
  delta0 = 0,
  p = 5,
  beta = NULL,
  rho = 0,
  cov_shift = rep(0, p),
  shape = 1.2,
  lambda = 0.02,
  target_cens = 0.2
)

Arguments

nI1	Number of internal randomized treated subjects.
nI0	Number of internal randomized concurrent control subjects.
nE	Number of external control subjects.
theta0	True treatment effect (log hazard ratio).
delta0	True population drift (log hazard ratio for external vs. internal controls).
p	Number of covariates; use 0 for the no-covariate setting.
beta	Numeric vector of covariate coefficients (length p). Defaults to rep(0.2, p).
rho	Equicorrelation of covariates.
cov_shift	Covariate mean shift in the external control arm (numeric vector of length p).
shape	Weibull shape parameter for event-time generation.
lambda	Baseline scale parameter for event-time generation.
target_cens	Target right-censoring proportion.

Value

A list with components:

data

A data frame with time, status, T, Z, and covariates X1, ..., Xp.

truth

The true parameters used to generate the data.

settings

The simulation settings, including the calibrated censoring rate.

Examples

set.seed(1)
sim <- simulate_hybrid_cox(nI1 = 100, nI0 = 100, nE = 200,
                           theta0 = log(0.8), delta0 = 0)
head(sim$data)

fdb documentation built on Oct. 4, 2026, 5:07 p.m.