/CDTE

Robust and Agnostic Learning of Conditional Distributional Treatment Effects

Primary LanguagePythonMIT LicenseMIT

CDTE

Tools for estimating quantile, super-quantile and f-risk conditional distributional treatment effects.

Replication code for Robust and Agnostic Learning of Conditional Distributional Treatment Effects.

Requirements

Replication code

  • For Figure 2, run python csqte_sims.py
  • For Figure 3, Figure 6 & Table 1, run python 401k.py
  • For Figure 4, run python cqte_sims.py
  • For Figure 5, run python cklrte_sims.py

Note: the original results were obtained using an Amazon Web Services instance with 32 vCPUs and 64 GiB of RAM. These results might take longer to run on other machines.