plot_predicted_common_support: Plot a regression tree predicting variables with lack of...

In joemarlo/plotBart: Diagnostic and Plotting Functions to Supplement 'bartCause'

Plot a regression tree predicting variables with lack of overlap

Description

Identify variables that predict lack of overlap

Usage

plot_predicted_common_support(
  .model,
  max_depth = 3,
  rule = c("both", "sd", "chi")
)

Arguments

.model	a model produced by 'bartCause::bartc()'
max_depth	a number indicatin the max depth of the tree. Higher numbers are more prone to overfitting.
rule	one of c('both', 'sd', 'chi') denoting which rule to use to identify lack of support

Value

ggplot object

Author(s)

George Perrett, Joseph Marlo

Examples

data(lalonde)
confounders <- c('age', 'educ', 'black', 'hisp', 'married', 'nodegr')
model_results <- bartCause::bartc(
 response = lalonde[['re78']],
 treatment = lalonde[['treat']],
 confounders = as.matrix(lalonde[, confounders]),
 estimand = 'ate',
 commonSuprule = 'none'
)
plot_predicted_common_support (model_results)
plot_predicted_common_support (model_results, max_depth = 2, rule = 'chi')

joemarlo/plotBart documentation built on May 31, 2024, 12:22 p.m.