Plot RD Always-assigned Share

This function creates a plot for the share of always-assigned units in a Regression Discontinuity (RD) design, either Sharp RD (SRD) or Fuzzy RD (FRD). It provides options to include various confidence intervals and reference lines.

plot_rd_aa_share(
  data,
  rd_type = "SRD",
  x_label = "Share of Always-assigned Units",
  y_label = "ATE",
  plot_title = "",
  theme_use = causalverse::ama_theme(),
  tau = TRUE,
  tau_CI = FALSE,
  bounds_CI = TRUE,
  ref_line = 0,
  ...
)

Arguments

data

The output object from the rdbounds function.

rd_type

The type of RD design, either "SRD" for Sharp RD or "FRD" for Fuzzy RD. Default is "SRD".

x_label

The label for the x-axis. Default is "Share of Always-assigned Units".

y_label

The label for the y-axis. Default is "ATE".

plot_title

The title of the plot. Default is an empty string.

theme_use

A ggplot2 theme function to apply to the plot. Default is causalverse::ama_theme().

tau

Logical, whether to include a vertical line at the estimated treatment effect. Default is TRUE.

tau_CI

Logical, whether to include confidence intervals for the treatment effect estimate. Default is FALSE.

bounds_CI

Logical, whether to include confidence intervals for the manipulation bounds. Default is TRUE.

ref_line

The y-intercept for a reference line. Default is 0.

...

Additional arguments passed to labs in ggplot2.

Value

A ggplot object.

Examples

if (FALSE) {
set.seed(1)
data <- rdbounds::rdbounds_sampledata(10000, covs = FALSE)
rdbounds_est_tau <- rdbounds::rdbounds(
    y = data$y,
    x = data$x,
    treatment = data$treatment,
    c = 0,
    discrete_x = FALSE,
    discrete_y = FALSE,
    bwsx = c(.2, .5),
    bwy = 1,
    kernel = "epanechnikov",
    orders = 1,
    evaluation_ys = seq(from = 0, to = 15, by = 1),
    refinement_A = TRUE,
    refinement_B = TRUE,
    right_effects = TRUE,
    potential_taus = c(.025, .05, .1, .2),
    yextremes = c(0, 15),
    num_bootstraps = 5
)
plot_rd_aa_share(rdbounds_est_tau)
}