Omitted-variable bias on a fitted model (sensemakr extender) — morie_sensitivity_omitted_var

Thin interface to sensemakr::sensemakr: returns the full Cinelli-Hazlett robustness-value object including benchmark bounds, adjusted t-statistics, and the data needed to draw contour plots. Pairs with omitted_variable_bias, which is the closed-form version that takes estimate + se + degrees of freedom directly (useful when you don't have an lm object handy).

Usage

morie_sensitivity_omitted_var_bias(
  model,
  treatment,
  benchmark_covariates = NULL,
  kd = c(1, 2, 3),
  ky = NULL,
  q = 1,
  alpha = 0.05,
  ...
)

Arguments

model: A fitted regression model (lm or compatible).
treatment: Name of the treatment variable (coefficient).
benchmark_covariates: Optional character vector of covariate names whose strengths bound the unmeasured-confounder strength.
kd: Multipliers on the benchmark covariate strength. Default c(1, 2, 3).
ky: Multipliers on the benchmark covariate's outcome strength. Default equal to kd.
q: Fraction of the estimate to be explained away. Default 1.
alpha: Significance level. Default 0.05.
...: Additional arguments forwarded to sensemakr::sensemakr.

Value

A list of class morie_sensitivity_omitted_var_bias with the robustness values, partial R-squared of treatment, benchmark bounds, and the full sensemakr object as raw.

References

Cinelli, C., & Hazlett, C. (2020). Making sense of sensitivity: extending omitted variable bias. Journal of the Royal Statistical Society B, 82(1), 39–67.

Examples

if (requireNamespace("sensemakr", quietly = TRUE)) {
  set.seed(1)
  df <- data.frame(d = rnorm(100), x1 = rnorm(100))
  df$y <- 0.5 * df$d + 0.3 * df$x1 + rnorm(100)
  fit <- stats::lm(y ~ d + x1, data = df)
  res <- morie_sensitivity_omitted_var_bias(fit, "d",
                                            benchmark_covariates = "x1")
  class(res)
}
#> [1] "morie_sensitivity_omitted_var_bias" "list"