bunsen (version 0.1.1)

get_point_estimate: Calculate the marginal treatment effects (only the point estimate) for hazard ratio (HR) adjusting covariates in clinical trials

Description

This function only estimates the marginal logHR. For a complete estimation including the standard error, see get_marginal_effect.

Usage

get_point_estimate(
  trt,
  cox_event,
  cox_censor,
  data,
  M = 1000,
  seed = NULL,
  cpp = TRUE,
  control = clmqControl(),
  verbose = TRUE
)

Value

The marginal beta (logHR)

Arguments

trt

Character. Variable name of the treatment assignment. Only support two arm trial at the moment.

cox_event

Object. A coxph model using the survival time and survival status.

cox_censor

Object. A coxph model using the survival time and 1-survival status.

data

A data frame used for cox_event and cox_censor.

M

Numeric. The number of simulated counterfactual patients. Suggest to set a large M to get robust estimation but this will be time comsuming.

seed

Numeric. Random seed for simulation.

cpp

Bool. True for using C++ optimization. False for not using C++ optimization. This requires cpp package installed.

control

Named list. A list containing control parameters, including memory of remote workers, whether to use nested parallel computation or local multiprocess, number of remote workers/jobs, etc. See details of clmqControl.

verbose

Bool. Print status messages. Default: TRUE

Details

Use the simulation approach from Daniel et al. (2020) to estimate the marginal HR when adjusting covariates. This function uses the parallel computation via remote LSF and local multiprocess. Additional feature also includes the C++ optimization that can speed up the calculation.

References

Daniel R, Zhang J, Farewell D. Making apples from oranges: Comparing noncollapsible effect estimators and their standard errors after adjustment for different covariate sets. Biom J. 2021;63(3):528-557. doi:10.1002/bimj.201900297

Examples

library(survival)
data("oak")

cox_event <- coxph(Surv(OS, os.status) ~ trt + btmb + pdl1, data = oak)
#
cox_censor <- coxph(Surv(OS, 1 - os.status) ~ trt + btmb + pdl1, data = oak)
#
get_point_estimate(
  trt = "trt", cox_event = cox_event, cox_censor, M = 1000, data = oak,
  seed = 1, cpp = FALSE, control = clmqControl(clmq_hr=FALSE)
)