Accelerated Foundation in Applied Causal InferenceFor Economists · 15 modules · 45 lessons
Part III · Advanced Causal Machine Learning

Module 08. Heterogeneous Effects & Policy Learning

Move from 'does it work?' to 'for whom?', then turn effect estimates into budget-constrained rules.

Social services: optimal targeting of retraining stipends for the unemployed about 6 hours3 lessons
Module progress0/3 lessons · 0%
Lessons
8.1

Conditional Average Treatment Effects and Meta-Learners

  • · Define the CATE and explain why the ATE can hide who benefits
  • · Implement S-, T- and X-learners with scikit-learn
  • · Evaluate CATE estimates against the truth in a simulation (PEHE)
120 min 6 Colab cellsVideo coming soon
8.2

Causal Forests with EconML

  • · Explain how a causal forest adapts random forests to estimate treatment effects honestly
  • · Fit a CausalForestDML model with EconML, separating effect modifiers (X) from controls (W)
  • · Report CATEs with confidence intervals and identify the main drivers of heterogeneity
120 min 4 Colab cellsVideo coming soon
8.3

Policy Learning: Who Should Be Treated?

  • · Turn CATE estimates into a treatment rule under a budget constraint
  • · Evaluate the value of a policy honestly with doubly robust scores on held-out data
  • · Learn a transparent, shallow policy tree that a ministry can apply
120 min 6 Colab cellsVideo coming soon