Practical R example – back door versus front door

Let’s consider a corporate scenario where we are interested in investigating the causal effect of gender on remuneration. We will consider both back door and front door adjustments using R. In real-world corporate settings, this analysis can be complex due to various factors, such as job role, seniority, education, work experience, and potential unmeasured confounders, such as negotiation skills or networking.

Synthetic data

Here is the R code to create a synthetic dataset; let’s name it corp_data and add relevant columns such as gender, remuneration, promotion_opportunities, performance_rating, department, work_experience, education, and job_role:

# Load necessary library
library(dplyr)
# Set seed for reproducibility
set.seed(123)
# Generate synthetic data
n <- 5000 # Number of observations
corp_data <- data.frame(
  gender = sample(c("Male", "Female"), n, replace =...