Does the new sensitivity analysis feature also work for CATE?
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.8k
- Forks
- 827
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
I saw there is a new sensitivity analysis feature since a few weeks and I am using it for my analysis because I was already using the LinearDRLearner. I have two questions
- In the line here, is the definition of rho missing?
- Can I get sensitivity analysis for CATE estimates as well somehow? For instance it's possible to get an ATE interval using
est.ate_interval(X=X_subset)where est is a LinearDRLearner instance. Could I get the sensitivity summary for this subset without fitting a separate model onX_subset?
I would offer to work on both of these if they are not done yet and if they make sense.
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 LinearDRLearner entry point and its ate_interval(X=X_subset) usage. Review how the existing sensitivity analysis defines rho, then determine whether a sensitivity summary can be produced for CATE estimates on a subset without fitting a separate model; done means both questions have documented, tested answers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100