py-why / py-why/EconML

multiple treatments confounding

Open
#525 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.8k
Forks
827
PR merge metrics
No merged PRs in 30d

Description

@vsyrgkanis
for multiple treatments, is it valid to use Treatment A in the propensity model for Treatment B?

for example would we want to estimate f1 as E[T1|X, W T2]?
if T2 is a potential confounder of T1 and Y, I dont think the econML package does this,is this a functionality that could be added? Is there a reason it wasnt, that I am not understanding?

My fear is that if we dont do this we could have co-linearity between the treatment effects in the final stage model

https://us-prod.asyncgw.teams.microsoft.com/v1/objects/0-eus-d9-3c39d23fd75ac3112d217460324ece37/views/imgo

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. First clarify the intended multiple-treatment propensity modeling behavior and review the relevant EconML treatment-effect implementation and tests; done would require an agreed design, implementation scope, and validation for the proposed functionality.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.