Interpretation ATE and interactions between treatment and covariates
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.8k
- Forks
- 827
- PR merge metrics
- No merged PRs in 30d
Description
Hello @kbattocchi
First of all thank you for your package, extremely useful. I have several questions about it. First let me introduce some context. My goal is to find among a set of features the features that would be causal to an output. My approach is as follows, I loop over the set of features by setting them one by one as treatments and setting the others as covariates and calculate the ATE using CausalForestDML.ate(X_test) with X_test the test part of the covariates.
My questions are as follows:
If the approach is the right one, how would it be possible to interpret the ATE? Is it normal to have results greater than 1?
Are the interactions between the treatment and the covariates taken into account?
Is the interpretation of the ATE relative or absolute?
Thank you in advance. Thank you very much.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the CausalForestDML.ate(X_test) usage described in the issue and identify the relevant existing explanation of ATE interpretation. Document how values, treatment-covariate interactions, and relative versus absolute effects should be understood; done means these questions are answered clearly for users.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100