Bias-adjusted treatment effect (Ding & VanderWeele 2016)

Bias-adjusted treatment effect (Ding & VanderWeele 2016)

Usage

bias_adjusted_estimate(estimate, se, rr_ud, rr_eu, prevalence_confounder = 0.5)

Arguments

estimate

Observed treatment effect on the log-RR / coefficient scale.

se

Standard error.

rr_ud

RR linking confounder to outcome.

rr_eu

RR linking treatment to confounder.

prevalence_confounder

Confounder prevalence. Default 0.5.

Value

Named list with adjusted_estimate, bias, adjusted_ci_lower, adjusted_ci_upper, original_estimate.

Examples

res <- bias_adjusted_estimate(0.5, 0.1, rr_ud = 2, rr_eu = 2)
res$adjusted_estimate
#> [1] 0.5
c(res$adjusted_ci_lower, res$adjusted_ci_upper)
#> [1] 0.304 0.696