G-Computation

Use the synthetic data setup first; it defines data and the columns used below. These are advanced direct R examples.

Average model-predicted outcomes under specified exposure contrasts.

gcomp_result <- causal_gcomp(data, "Immunotherapy", "Response",
                             confounders = c("Age", "Sex", "Stage", "ECOG"),
                             outcome_type = "binary",
                             boot_R = 500)

Read the result

Binary-outcome contrasts can include RiskDiff, RiskRatio and MarginalOR. Keep the requested exposure contrast and bootstrap settings. Eligible survival paths target RMST or survival-probability differences, not a hazard ratio.

See effect scales and reporting, diagnostics and the current support reference.