Plot weights across a continuous covariate

Source: R/plot_continuous.R

This provides a simple plot for the distribution of a single continuous covariate in the nominal sample and the implicit sample defined by the Aronow and Samii (2015) doi:10.1111/ajps.12185 regression weights.

plot_weighting_continuous(mod, covariate, alpha = 0.05, num_eval = 250, ...)

Arguments

mod

Weighting model object

covariate

Covariate vector

alpha

Number between zero and one indicating the desired alpha level for confidence intervals.

num_eval

Number of points at which to evaluate the density.

...

unused arguments

Value

A ggplot2::ggplot object.

Details

Kernel density estimates use the bias-corrected methods of Cattaneo et al (2020).

References

  • Cattaneo, Jansson and Ma (2021): lpdensity: Local Polynomial Density Estimation and Inference. Journal of Statistical Software, forthcoming.

  • Cattaneo, Jansson and Ma (2020): Simple Local Polynomial Density Estimators. Journal of the American Statistical Association 115(531): 1449-1455.

Examples

y <- rnorm(100)
a <- rbinom(100, 1, 0.5)
x <- rnorm(100)
cov <- runif(100)
mod <- stats::lm(y ~ a + x)
rw_mod <- calculate_weights(mod, "a")
plot_weighting_continuous(rw_mod, cov, num_eval = 25)